# Using Auggie with Automation
Source: https://docs.augmentcode.com/cli/automation

Auggie was designed to not just be a powerful agent to write code, but to automate all the tasks that are needed to build software at scale.

## About automation

Auggie was purpose built to integrate into your software development stack. From using Auggie in your local development workflows to automatically running Auggie in your CI/CD pipelines, Auggie can help you build better software faster.

### Example use cases

* **Code reviews**: Review code changes and provide feedback.
* **Issue triage**: Triage incoming issues and route them to the appropriate team or individual.
* **Automate on-call**: Respond to incoming alerts and create an assessment plan.
* **Exception management**: Analyze incoming exceptions and create tickets.

## Integrating with your workflows

In order to use Auggie in your systems, like a CI/CD pipeline, you'll need to install Auggie CLI, provide a session token, and write an instruction that will be used alongside any data from your system you want to include.

### Installation

Auggie can be [installed](/cli/setup-auggie/install-auggie-cli) directly from npm anywhere you can run Node 22 or later including VMs, serverless functions, and containers. You will also need to install any dependencies for defined MCP servers in those environments.

```sh
npm install -g @augmentcode/auggie
```

### Authentication

Session tokens are associated with the user that created it, and Auggie will run with integration configurations from that user. See [Authentication](/cli/setup-auggie/authentication) for full details. You can override the user's GitHub configuration by passing `--github-api-token <token>`.

```sh
# First, login to Augment with the CLI
auggie --login

# Next, output your token
auggie --print-augment-token

# Then, pass your token to auggie
AUGMENT_SESSION_AUTH='<token>' auggie --print "Summarize the build failure"
```

### Scripts and pipes

Auggie runs as a subprocess, so it can be used in any shell script. It can be used just like any command-line tool that follows the Unix philosophy. You can pipe data into Auggie and then pipe the response to another command. Data passed into Auggie through stdin will be used as context in addition to the instruction.

```sh
# Pipe data through stdin
cat build.log | auggie --print "Summarize the failure and open a Linear ticket"

# Provide input from a file
auggie --compact --instruction /path/to/instruction.md < build.log
```

## GitHub Actions

GitHub Actions makes it easy to connect Auggie to other parts of your software development pipeline, from linting, testing, build, and deploy. We've built a [simple wrapper for Auggie](https://github.com/augmentcode/augment-agent) that enables you to  integrate with GitHub Action workflows and build custom tooling around Auggie.

Follow the instructions to [configure Augment Agent](https://github.com/augmentcode/augment-agent/blob/main/README.md) in GitHub Actions and explore the [example-workflows](https://github.com/augmentcode/augment-agent/tree/main/example-workflows) directory to get started.

### Ready to use workflows

Get started using Auggie in GitHub Actions immediately by following the instructions for setup and deploy in one of the following workflows, or use the `/github-workflow` wizard in Auggie to have the workflows generated for you.

* [PR Description](https://github.com/augmentcode/describe-pr): This action automatically analyzes your PR changes and generates comprehensive, informative descriptions.
* [PR Review](https://github.com/augmentcode/review-pr): This action automatically analyzes your PR changes and generates comprehensive, informative reviews

Need even more help building GitHub Actions? May we suggest asking Auggie.

```sh
auggie "Help me build a GitHub Action to..."
```


# Custom Slash Commands
Source: https://docs.augmentcode.com/cli/custom-commands

Create and manage custom slash commands for frequently-used prompts and workflows.

## About Custom Slash Commands

Custom slash commands let you create reusable prompts stored as Markdown files that Auggie can run. You can organize commands by scope (workspace or user) and use directory structures for namespacing.

### Syntax

```
/<command-name> [arguments]
```

### Parameters

| Parameter        | Description                              |
| :--------------- | :--------------------------------------- |
| `<command-name>` | Name derived from the Markdown filename  |
| `[arguments]`    | Optional arguments passed to the command |

## Command Types and Locations

Custom commands are stored in markdown files and can be placed in multiple locations with a specific order of precedence:

### Command Locations (in order of precedence)

1. **User Commands**: `~/.augment/commands/<name>.md` (user)
2. **Workspace Commands**: `./.augment/commands/<name>.md` (workspace)
3. **Claude Code Commands**: `./.claude/commands/<name>.md` (.claude)

### User Commands

Commands available across all your projects. These are user-wide and persist across different workspaces.

**Location**: `~/.augment/commands/`

```sh
# Create a global command
mkdir -p ~/.augment/commands
echo "Review this code for security vulnerabilities:" > ~/.augment/commands/security-review.md
```

### Workspace Commands

Commands stored in your repository and shared with your team. These are workspace-specific and can be committed to version control.

**Location**: `./.augment/commands/`

```sh
# Create a workspace command
mkdir -p .augment/commands
echo "Analyze this code for performance issues and suggest optimizations:" > .augment/commands/optimize.md
```

### Claude Code Compatibility

Auggie automatically detects and supports commands from `./.claude/commands/` for compatibility with existing Claude Code setups. This allows teams already using Claude Code to continue using their existing command libraries without modification.

**Location**: `./.claude/commands/` and `~/.claude/commands/`

**Migration**: While `./.claude/commands/` is supported for compatibility, we recommend migrating to `./.augment/commands/` for new projects to maintain consistency with Auggie's naming conventions.

## Features

### Namespacing

Organize commands in subdirectories. Commands from nested directories can be accessed using the `namespace:command` syntax, where the namespace corresponds to the subdirectory name.

For example, a file at `.augment/commands/frontend/component.md` creates the command `/frontend:component`.

Conflicts between user and workspace level commands are not supported and will be defined in order of precedence above.

### Arguments

Pass dynamic values to commands.

```markdown
# Command definition
echo 'Fix issue following our coding standards' > .augment/commands/fix-issue.md

# Usage
> /fix-issue 123
```

### Frontmatter

Command files support frontmatter for metadata:

| Frontmatter     | Purpose                                                                    | Default                             |
| :-------------- | :------------------------------------------------------------------------- | :---------------------------------- |
| `description`   | Brief description of the command                                           | Uses the first line from the prompt |
| `argument-hint` | Expected arguments format that will be displayed after typing in a command | None                                |
| `model`         | Specify the model to run this command with (overrides the CLI default)     | Uses the CLI default model          |

**File**: `~/.augment/commands/deploy-staging.md`

```markdown
---
description: Deploy the application to staging with health checks
argument-hint: [branch-name]
model: gpt-4o
---

Deploy the application to the staging environment:

1. Run all tests to ensure code quality
2. Build the application for production
3. Deploy to staging server
4. Run health checks to verify deployment
5. Send notification to team channel
```

## Command Line Execution

We also provide the ability to execute custom commands from the command line using the `auggie command <your_command>` or list them with `auggie command list`. For complete command-line reference, see [CLI Reference for Custom Commands](/cli/reference#custom-commands).

```sh
# Execute a custom command
auggie command deploy-staging

# List all available commands (including custom ones)
auggie command list
```

Custom commands appear in the help output with their descriptions:

```
Available custom commands:
  auggie command deploy-staging    # Deploy the application to staging
  auggie command security-review   # Review code for security vulnerabilities
```

## Example Commands

For ready-to-use examples of custom slash commands, including code review templates, bug fix guides, and feature implementation plans, see:

**[Custom Commands Examples](/cli/custom-commands-examples)**

## Best Practices

1. **Use kebab-case naming** for command names (e.g., `deploy-staging`, `run-tests`)
2. **Keep names descriptive** but concise, avoiding spaces and special characters
3. **Use meaningful prefixes** for related commands (e.g., `deploy-staging`, `deploy-production`)
4. **Include clear descriptions** in frontmatter for better discoverability
5. **Break complex workflows** into numbered steps for clarity
6. **Use user commands** (`~/.augment/commands/`) for personal workflows across all projects
7. **Use workspace commands** (`./.augment/commands/`) for team-shared, project-specific tasks
8. **Organize with subdirectories** for related command groups using namespacing
9. **Document command purpose** and expected outcomes clearly
10. **Version your commands** when making significant changes

## See Also

* [Custom Commands Examples](/cli/custom-commands-examples) - Ready-to-use command templates and examples
* [Interactive Mode Slash Commands](/cli/interactive#slash-commands) - Learn about Auggie's interactive terminal features
* [CLI Reference for Custom Commands](/cli/reference#custom-commands) - Complete reference for command-line flags


# Custom Slash Commands Examples
Source: https://docs.augmentcode.com/cli/custom-commands-examples

Ready-to-use examples of custom slash commands for common development workflows.

## Example Commands

Here are some practical examples of custom slash commands you can use in your projects:

<AccordionGroup>
  <Accordion title="Code Review Command">
    ```markdown
    ---
    description: Perform a comprehensive code review
    argument-hint: [file-path]
    ---

    Please perform a comprehensive code review of the specified file or current changes, focusing on:

    1. **Code Quality**: Check for readability, maintainability, and adherence to best practices
    2. **Security**: Look for potential security vulnerabilities
    3. **Performance**: Identify potential performance issues
    4. **Testing**: Suggest areas that need test coverage
    5. **Documentation**: Check if code is properly documented

    $ARGUMENTS
    ```
  </Accordion>

  <Accordion title="Bug Fix Template">
    ```markdown
    ---
    description: Generate a structured bug fix approach
    argument-hint: [bug-description]
    ---

    Help me fix this bug: $ARGUMENTS

    Please provide:
    1. Root cause analysis
    2. Step-by-step fix approach
    3. Testing strategy
    4. Prevention measures for similar issues
    ```
  </Accordion>

  <Accordion title="Feature Implementation Guide">
    ```markdown
    ---
    description: Create implementation plan for new features
    argument-hint: [feature-description]
    ---

    Create a detailed implementation plan for: $ARGUMENTS

    Include:
    - Technical requirements
    - Architecture considerations
    - Implementation steps
    - Testing approach
    - Documentation needs
    ```
  </Accordion>

  <Accordion title="Security Review Command">
    ```markdown
    ---
    description: Perform security analysis on code
    argument-hint: [file-path]
    ---

    Perform a security review of: $ARGUMENTS

    Focus on:
    1. **Input validation** and sanitization
    2. **Authentication** and authorization checks
    3. **Data exposure** and privacy concerns
    4. **Injection vulnerabilities** (SQL, XSS, etc.)
    5. **Cryptographic** implementations
    6. **Dependencies** with known vulnerabilities

    Provide specific recommendations for any issues found.
    ```
  </Accordion>

  <Accordion title="Performance Optimization">
    ```markdown
    ---
    description: Analyze and optimize code performance
    argument-hint: [file-path]
    ---

    Analyze the performance of: $ARGUMENTS

    Please examine:
    1. **Algorithm complexity** and efficiency
    2. **Memory usage** patterns
    3. **Database queries** and optimization opportunities
    4. **Caching** strategies
    5. **Network requests** and bundling
    6. **Rendering performance** (for frontend code)

    Suggest specific optimizations with expected impact.
    ```
  </Accordion>

  <Accordion title="Documentation Generator">
    ```markdown
    ---
    description: Generate comprehensive documentation
    argument-hint: [file-path]
    ---

    Generate documentation for: $ARGUMENTS

    Include:
    1. **Overview** and purpose
    2. **API reference** with parameters and return values
    3. **Usage examples** with code snippets
    4. **Configuration options** if applicable
    5. **Error handling** and troubleshooting
    6. **Dependencies** and requirements

    Format as clear, structured markdown.
    ```
  </Accordion>

  <Accordion title="Test Generation Command">
    ```markdown
    ---
    description: Generate comprehensive test cases
    argument-hint: [file-path]
    ---

    Generate test cases for: $ARGUMENTS

    Create tests covering:
    1. **Happy path** scenarios
    2. **Edge cases** and boundary conditions
    3. **Error handling** and exceptions
    4. **Integration points** with other components
    5. **Performance** considerations
    6. **Security** edge cases

    Use appropriate testing framework conventions and include setup/teardown as needed.
    ```
  </Accordion>
</AccordionGroup>

## How to Add Commands to Your Project

To use these custom slash commands in your project, you need to save them in the `.augment/commands/` directory:

### Step 1: Create the Commands Directory

First, create the `.augment/commands/` directory in your project root if it doesn't exist:

```bash
mkdir -p .augment/commands
```

### Step 2: Save Command Files

Save each command as a separate `.md` file in the `.augment/commands/` directory. For example:

```bash
# Save the code review command
cat > .augment/commands/code-review.md << 'EOF'
---
description: Perform a comprehensive code review
argument-hint: [file-path]
---

Please perform a comprehensive code review of the specified file or current changes, focusing on:

1. **Code Quality**: Check for readability, maintainability, and adherence to best practices
2. **Security**: Look for potential security vulnerabilities
3. **Performance**: Identify potential performance issues
4. **Testing**: Suggest areas that need test coverage
5. **Documentation**: Check if code is properly documented

$ARGUMENTS
EOF
```

### Step 3: Use Your Commands

Once saved, your custom commands become available as slash commands in Augment:

```
/code-review src/components/Button.tsx
/bug-fix "Login form validation not working"
/security-review auth/middleware.js
```

### Directory Structure

Your project structure should look like this:

```
your-project/
├── .augment/
│   └── commands/
│       ├── code-review.md
│       ├── bug-fix.md
│       ├── security-review.md
│       └── performance-optimization.md
├── src/
└── package.json
```

## Usage Tips

* **Save these templates** in your `.augment/commands/` directory
* **Customize the prompts** to match your team's coding standards and practices
* **Add project-specific context** to make the commands more effective
* **Combine commands** by referencing outputs from one command in another
* **Use meaningful filenames** like `code-review.md`, `bug-fix.md`, etc.
* **Version control your commands** by committing the `.augment/commands/` directory to your repository

## Creating Your Own Examples

When creating custom commands, consider these patterns:

1. **Start with a clear description** in the frontmatter
2. **Use argument hints** to guide users on expected inputs
3. **Structure your prompts** with numbered lists or bullet points
4. **Include specific instructions** for the type of analysis or output you want
5. **Reference the `$ARGUMENTS` variable** where user input should be inserted

## See Also

* [Custom Slash Commands](/cli/custom-commands) - Learn how to create and manage custom commands
* [CLI Reference for Custom Commands](/cli/reference#custom-commands) - Complete command-line reference for custom commands


# Integrations and MCP
Source: https://docs.augmentcode.com/cli/integrations

Expand Augment's capabilities with external tools and data sources through native integrations and Model Context Protocol (MCP) servers.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

<Note>Auggie runs commands and tools automatically. Only use integrations and MCP servers from trusted sources, and be aware of the risks of combining multiple tools with external data sources or production systems.</Note>

## About Integrations and MCP

Auggie can utilize external integrations through native integrations like GitHub, Linear, and Notion and Model Context Protocol (MCP) to access external systems for information and integrate tools to take actions. MCP is an open protocol that provides a standardized way to connect AI models to different data sources and tools.

## Native Integrations

You'll need to configure the integration in Augment for VS Code or JetBrains IDEs. Once configured, the integration will be available for use with Auggie automatically. See a full list and examples for [native agent integrations](/setup-augment/agent-integrations).

### 1. Setup in Augment extension

* **Visual Studio Code**: Click the settings icon in the top right of Augment's chat window or press <Keyboard shortcut="Cmd/Ctrl Shift P" /> and select <Command text="Show Settings Panel" />
* **JetBrains IDEs**: Click the Augment icon in the bottom right of your JetBrains IDE and select <Command text="Tool Settings" />

### 2. Connect the integration

Click "Connect" for the integration you want to set up

<img className="block rounded-xl" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=89a56ce1b2adfceeff53aa5c2c7e1e3d" alt="Set up integrations in the settings page" width="1096" height="598" data-path="images/integration-settings.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=280&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=340403281e17bb92431e2d8256147913 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=560&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5181e8e7a090238dc17c4bf037af62a4 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=840&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f3549289d4e1246092e524dbd7a012fc 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=1100&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=edf707f8b5706d828f47005b842d574e 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=1650&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a17cb3a8b511caeb927cd707398e4c28 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=2500&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8863d6e3a97b999eada3abab0279cc82 2500w" data-optimize="true" data-opv="2" />

You'll be redirected to authorize the integration with the appropriate service. After authorization, the integration will be available for use with Augment Agent.

## MCP Integrations

In addition to native integrations, Auggie can also access external systems through Model Context Protocol (MCP) servers. MCP servers can be used to access local or remote databases, run automated browser testing, send messages to Slack, or even play music on Spotify.

You can use multiple MCP servers with Auggie by passing a JSON string or a path to a JSON file with the `--mcp-config` flag. You can pass the flag multiple times for multiple configurations. Some servers may require you to install dependencies on the host machine or containers.

```json
// After npm install gitlab-mr-mcp
{
  "mcpServers": {
    "gitlab-mr-mcp": {
      "command": "node",
      "args": ["/path/to/gitlab-mr-mcp/index.js"],
      "env": {
        "MR_MCP_GITLAB_TOKEN": "your_gitlab_token",
        "MR_MCP_GITLAB_HOST": "your_gitlab_host"
      }
    }
  }
}
```


# Interactive mode
Source: https://docs.augmentcode.com/cli/interactive

Use a rich interactive terminal experience to explore your codebase, build new features, debug issues, and integrate your tools.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

<Note>Auggie is currently in beta and does not support all features available in the Augment plugins for Visual Studio Code or JetBrains IDEs.</Note>

## About interactive mode

Auggie is an agentic terminal-based code assistant that has deep codebase knowledge powered by Augment's context engine. Auggie can help you understand a new codebase, fix bugs quickly, and build new features faster. Auggie has access to your connected integrations and MCP servers and can pull in additional context or run tools to get your tasks done.

## Using interactive mode

Run `auggie` without any mode flags to get the full-screen terminal user interface with rich interactive features, real-time streaming of responses, and visual progress indicators. This mode shows all tool calls, results, and allows ongoing conversation through an intuitive interface.

```sh
# Start Auggie in interactive mode
auggie

# Provide an initial instruction
auggie "Look at my open issues and prioritize the highest impact ones for me"
```

### Multi-line input

Entering a new line in the input box depends on your terminal configuration and platform. You can use `Ctrl + J` to enter a new line in any terminal. See below for instructions to configure your terminal to use `Option + Enter` to enter a new line.

| Terminal application       | New line shortcut |
| :------------------------- | :---------------- |
| All terminals              | `Ctrl + J`        |
| MacOS Terminal (see below) | `Option + Enter`  |
| iTerm2 (see below)         | `Option + Enter`  |
| VS Code Terminal           | `Option + Enter`  |
| Ghostty                    | `Shift + Enter`   |

**MacOS Terminal**

1. Go to <Command text="Terminal > Settings... > Profiles > Keyboard" />
2. Check <Command text="Use option key as meta key" />

**iTerm2**

1. Go to <Command text="iTerm2 > Settings... > Profiles > Keys" />
2. Check <Command text="Left or Right option key acts as Esc+" />

## Reference

### Shortcuts

| Command             | Description                                                 |
| :------------------ | :---------------------------------------------------------- |
| `Ctrl + P`          | Enhance your prompt with codebase context                   |
| `Escape`            | Interrupt the active agent                                  |
| `Ctrl + C`          | Interrupt the active agent                                  |
| `Escape` + `Escape` | Clear the input box                                         |
| `Ctrl + C`          | Press twice to exit                                         |
| `Ctrl + D`          | Press twice to exit                                         |
| `Up Arrow`          | Cycle through previous messages                             |
| `Down Arrow`        | Cycle through previous messages                             |
| `Ctrl + O`          | Open current input in external editor, inserts text on exit |

### Slash Commands

| Command            | Description                                                 |
| :----------------- | :---------------------------------------------------------- |
| `/account`         | Show account information                                    |
| `/clear`           | Clear the input box                                         |
| `/editor`          | Open current input in external editor, inserts text on exit |
| `/exit`            | Exit Auggie                                                 |
| `/feedback`        | Provide feedback to the Augment team                        |
| `/github-workflow` | Generate a GitHub Action workflow                           |
| `/help`            | Show help                                                   |
| `/logout`          | Logout of Augment                                           |
| `/mcp-status`      | View the status of all configured MCP servers               |
| `/model`           | Select the model for this session                           |
| `/new`             | Start a new conversation with no message history            |
| `/permissions`     | View and manage tool permissions                            |
| `/request-id`      | Show the request ID for the current conversation            |
| `/task`            | Open task manager to add, edit, and manage tasks            |
| `/verbose`         | Toggle verbose output for tools                             |
| `/vim`             | Toggle Vim mode for advanced text editing                   |

For more information about slash commands, including how to create custom commands, see [Custom Slash Commands](/cli/custom-commands).


# Prompt Enhancer
Source: https://docs.augmentcode.com/cli/interactive/prompt-enhancer

Use Ctrl+P to enhance your prompts with relevant context, structure, and conventions from your codebase.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## About the Prompt Enhancer

The Auggie CLI prompt enhancer is a powerful feature that helps you craft better prompts by automatically adding relevant context, structure, and conventions from your codebase. Instead of writing detailed prompts from scratch, you can start with a simple idea and let the prompt enhancer transform it into a comprehensive, well-structured prompt.

## Activating the Prompt Enhancer

To use the prompt enhancer in Auggie's interactive mode:

1. **Start typing your prompt** in the input box
2. **Press <Keyboard shortcut="Ctrl + P" />** to activate the prompt enhancer
3. **Wait for enhancement** - Auggie will process your prompt and replace it with an enhanced version
4. **Review and edit** the enhanced prompt if needed
5. **Submit your enhanced prompt** by pressing Enter

<Note>The prompt enhancer is only available when you have text entered at the command prompt. The <Keyboard shortcut="Ctrl + P" /> shortcut will only work in interactive mode.</Note>

## How It Works

When you press <Keyboard shortcut="Ctrl + P" />, the prompt enhancer:

1. **Captures your current input** and saves it to history
2. **Switches to Enhancement mode** - you'll see the mode indicator change and input will be temporarily disabled
3. **Sends your prompt** to the enhancement service using your current workspace context
4. **Processes the response** and extracts the enhanced prompt
5. **Replaces your input** with the enhanced version and returns to Normal mode

During enhancement, you'll see:

* The mode indicator shows "Enhancing your prompt, press Esc to cancel"
* Input is disabled to prevent conflicts
* A visual indication that processing is in progress

## Enhancement Process

The prompt enhancer uses your workspace context to improve your prompts by:

* **Adding relevant file references** from your current project
* **Including coding conventions** and patterns from your codebase
* **Structuring the prompt** for better clarity and specificity
* **Adding context** about your project's architecture and dependencies
* **Suggesting specific examples** based on existing code patterns

## Canceling Enhancement

You can cancel the prompt enhancement process at any time:

* **Press <Keyboard shortcut="Esc" />** to cancel enhancement and restore your original input
* **Press <Keyboard shortcut="Ctrl + C" />** to cancel enhancement and restore your original input

When canceled, you'll see a brief notification and your original prompt will be restored.

## Error Handling

If the prompt enhancement fails:

* Your original input will be restored
* An error notification will appear briefly (\~3 seconds)
* You can try enhancing again or proceed with your original prompt

Common reasons for enhancement failure:

* Network connectivity issues
* Service temporarily unavailable
* Input too short or unclear for enhancement

## Examples

### Before Enhancement

```
fix the login bug
```

### After Enhancement (Example)

```
Fix the authentication bug in the login flow. Please:

1. Review the current login implementation in `src/auth/login.ts`
2. Check for issues with token validation and session management
3. Examine error handling in the authentication middleware
4. Look at recent changes to the user authentication flow
5. Test the fix with both valid and invalid credentials
6. Ensure the fix follows our existing error handling patterns

Context: This appears to be related to the recent changes in the authentication system. Please maintain consistency with our existing auth patterns and ensure proper error messages are returned to the user.
```

## Integration with Other Features

The prompt enhancer works seamlessly with other Auggie CLI features:

* **History Navigation**: Enhanced prompts are added to your command history
* **Multi-line Input**: Works with both single-line and multi-line prompts
* **Conversation Context**: Uses your current conversation history for better enhancement
* **Workspace Awareness**: Leverages your current workspace and file context

## Tips for Best Results

1. **Start with clear intent** - Even simple prompts like "add tests" or "refactor this" work well
2. **Be specific about scope** - Mention specific files or components when relevant
3. **Use domain language** - Technical terms related to your project help the enhancer understand context
4. **Review enhanced prompts** - The enhancer provides a starting point; feel free to edit further
5. **Iterate if needed** - You can enhance the same prompt multiple times for different approaches

## Troubleshooting

**Ctrl+P doesn't work:**

* Ensure you have text in the input box
* Make sure you're in Normal mode (not in a menu or other mode)
* Check that you're using the correct key combination for your terminal

**Enhancement takes too long:**

* Press Esc to cancel and try again
* Check your network connection
* Try with a shorter or simpler prompt

**Enhanced prompt isn't helpful:**

* Edit the enhanced prompt manually
* Try starting with a more specific initial prompt
* Consider the context - the enhancer works best with workspace-relevant requests

## Related Features

* [Task Management](/cli/interactive/task-management) - Break down enhanced prompts into manageable tasks
* [Keyboard Shortcuts](/cli/interactive#shortcuts) - Learn other useful CLI shortcuts
* [Slash Commands](/cli/interactive#slash-commands) - Discover other interactive commands


# Using Task Manager
Source: https://docs.augmentcode.com/cli/interactive/task-management

Use /task to break down complex problems into manageable steps.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## About the Task Manager

The Auggie CLI task manager allows you to break down complex problems into discrete, manageable actions and track your progress through each step. It's particularly useful for automation workflows and keeping the agent focused on multi-step tasks.

The task manager maintains state per session and stores tasks under `~/.augment` for persistence across CLI sessions.

## Activating the Task Manager

Start Auggie in interactive mode and use the `/task` slash command:

```bash
# Start Auggie in interactive mode
auggie

# Then type the slash command
/task
```

This opens the task manager interface, which takes over the main panel and provides a focused environment for task management.

### Alternative Access

You can also ask the agent to create a task list for you:

```bash
auggie "Start a task list to implement user authentication"
```

The agent will automatically create and populate a task list when it encounters complex, multi-step problems.

## Task Manager Interface

The task manager provides a scrollable interface with comprehensive theming and visual feedback. When active, it replaces the main chat interface to provide a focused task management experience.

### Navigation and Interaction

Use your keyboard to interact with the Task Manager:

| Key        | Action                                                                                     |
| :--------- | :----------------------------------------------------------------------------------------- |
| `↑` / `↓`  | Navigate between tasks. The active task is highlighted with • next to the \[ ] Task Title. |
| `J` / `K`  | Alternative vim-style navigation (up/down)                                                 |
| `A`        | Add a new task                                                                             |
| `E`        | Edit the active task's title and description                                               |
| `D`        | Delete the active task                                                                     |
| `Spacebar` | Toggle task status                                                                         |
| `Esc`      | Dismiss the Task Manager                                                                   |

## Task Status Indicators

Tasks have three distinct states with corresponding visual status indicators:

* **\[ ] Not Started** - Empty checkbox, task has not been started
* **\[✓] Done** - Checkmark, task has been completed
* **\[-] Cancelled** - Dash, task has been cancelled or is no longer needed

## Working with Tasks

### Creating Tasks

**Manual Creation:**

1. Press `A` to add a new task
2. Enter the task title when prompted
3. Optionally add a description for more detailed context

**Agent-Generated Tasks:**
The agent automatically creates tasks inside the Task Manager when it encounters complex problems. You can also explicitly request task creation:

```bash
"Create a task list to refactor the authentication system"
```

### Editing Tasks

1. Navigate to the desired task using arrow keys or J/K
2. Press `E` to edit
3. Modify the title first, then the description
4. The task manager provides inline editing with clear visual feedback

### Task Execution

**Manual Execution:**

* Use the task list as a checklist, manually updating status as you complete work
* Toggle status with `Spacebar` to track progress

**Agent Execution:**
You can ask the agent to work on specific tasks from the task manager:

```bash
"Work on the first incomplete task in my task list"
"Complete the database migration task"
```

The agent will access your task list and update task status as it works.

## Advanced Features

### Task Hierarchy and Subtasks

The task manager supports nested task structures:

* Main tasks can have subtasks for complex workflows
* Subtasks are automatically indented and organized hierarchically
* Navigate through nested structures using standard navigation keys

### Persistence and Sessions

* Tasks are automatically saved per session under `~/.augment`
* Task lists persist across CLI restarts within the same session
* Each conversation session maintains its own task list

### Integration with Agent Workflow

The task manager is designed to work seamlessly with agent automation:

* **Keeps agents focused**: Provides clear structure for multi-step workflows
* **Progress tracking**: Agent can update task status as it completes work
* **Context preservation**: Tasks maintain context across long conversations
* **Automation-friendly**: Particularly useful for non-interactive automation workflows

## Use Cases and Examples

### Development Workflow

```bash
auggie "Create a task list to implement user registration feature"
# Agent creates tasks like:
# [ ] Design user registration API endpoints
# [ ] Create user model and database schema
# [ ] Implement registration validation
# [ ] Add password hashing and security
# [ ] Write unit tests for registration
# [ ] Update API documentation
```

### Code Refactoring

```bash
auggie "Break down refactoring the payment system into tasks"
# Agent creates structured tasks for complex refactoring
```

### Bug Investigation

```bash
auggie "Create tasks to investigate and fix the login timeout issue"
# Agent creates systematic debugging tasks
```

## Tips for Effective Task Management

1. **Be Specific**: Create clear, actionable task descriptions
2. **Break Down Complex Work**: Use subtasks for multi-step processes
3. **Regular Updates**: Keep task status current for accurate progress tracking
4. **Agent Collaboration**: Let the agent help create and organize task structures
5. **Session Organization**: Use task lists to maintain focus across long sessions

## Troubleshooting

**Task Manager Won't Open:**

* Ensure you're in interactive mode (`auggie` without `-p` flag)
* Try typing `/task` exactly as shown
* Check that you're not in the middle of another operation

**Tasks Not Persisting:**

* Tasks are saved per session - starting a new session creates a new task list
* Check that `~/.augment` directory has proper write permissions

**Navigation Issues:**

* Use either arrow keys (↑/↓) or vim keys (J/K) for navigation
* Ensure the task manager has focus (not in edit mode)

## Related Features

* [Prompt Enhancer](/cli/interactive/prompt-enhancer) - Enhance task descriptions with context
* [Keyboard Shortcuts](/cli/interactive#shortcuts) - Learn other useful CLI shortcuts
* [Slash Commands](/cli/interactive#slash-commands) - Discover other interactive commands


# Introducing Auggie CLI
Source: https://docs.augmentcode.com/cli/overview

Auggie in the terminal gives you powerful agentic capabilities to analyze code, make changes, and execute tools in an interactive terminal and in your automated workflows.

export const Availability = ({tags}) => {
  const tagTypes = {
    invite: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    beta: {
      styles: "border border-zinc-500/20 bg-zinc-50/50 dark:border-zinc-500/30 dark:bg-zinc-500/10 text-zinc-900 dark:text-zinc-200"
    },
    vscode: {
      styles: "border border-sky-500/20 bg-sky-50/50 dark:border-sky-500/30 dark:bg-sky-500/10 text-sky-900 dark:text-sky-200"
    },
    jetbrains: {
      styles: "border border-amber-500/20 bg-amber-50/50 dark:border-amber-500/30 dark:bg-amber-500/10 text-amber-900 dark:text-amber-200"
    },
    vim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    neovim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    default: {
      styles: "bg-gray-200"
    }
  };
  return <div className="flex items-center space-x-2 border-b pb-4 border-gray-200 dark:border-white/10">
      <span className="text-sm font-medium">Availability</span>
      {tags.map(tag => {
    const tagType = tagTypes[tag] || tagTypes.default;
    return <div key={tag} className={`px-2 py-0.5 rounded-md text-xs font-medium ${tagType.styles}`}>
            {tag}
          </div>;
  })}
    </div>;
};

<Availability tags={["beta", "limited release"]} />

## Introduction

Auggie CLI takes the power of Augment's agent and context engine and puts it in your terminal, allowing you to use Augment anywhere your code goes. You can use Auggie in a standalone interactive terminal session alongside your favorite editor or in any part of your software development stack.

* Build features and debug issues with a standalone interactive agent.
* Get instant feedback, insight, and suggestions for your PRs and builds.
* Triage customer issues and alerts from your observability stack.

## Getting started

To use Auggie CLI in interactive mode or in your automations, you'll need:

* Node 22 or later installed
* A compatible shell like zsh, bash, fish

<Steps>
  <Step title="Install Auggie with npm">
    ```sh
    npm install -g @augmentcode/auggie
    ```

    You can install Auggie CLI directly from npm anywhere you can run Node 22 or later. Auggie is currently in beta and may not run on all environments and terminal configurations.
  </Step>

  <Step title="Go to your project directory">
    ```sh
    cd /path/to/your/project
    ```

    Your project will be indexed automatically when you run Auggie in your project directory. Augment's powerful context engine provides the best results when it has access to your project's codebase and any related repositories.
  </Step>

  <Step title="Login or sign up to Augment">
    ```sh
    auggie login
    ```

    After installing, you'll have to log in to your Augment account. Run auggie login and follow the prompts.
  </Step>

  <Step title="Start using Auggie">
    ```sh
    auggie "optional initial prompt"
    ```

    Just run `auggie` to start the interactive terminal. You can also pass a prompt as an argument and use `--print` to print the response to stdout instead of the interactive terminal–perfect for automation workflows.
  </Step>
</Steps>

## Using Auggie in interactive mode

Run `auggie` without any mode flags to get the full-screen terminal user interface with rich interactive features, real-time streaming of responses, and visual progress indicators. This mode shows all tool calls, results, and allows ongoing conversation through an intuitive interface.

Best for manual development work, exploration, and interactive problem-solving sessions where you want the full visual experience and plan to have back-and-forth conversations with the agent.

## Using Auggie in your automations

**Print Mode**: Add the `--print` flag (e.g., `auggie --print "your instruction"`) to execute the instruction once without the UI. This mode exits immediately without prompting for additional input. Perfect for automation, CI/CD pipelines, and background tasks where you want the agent to act without follow-up from a person.

**Quiet Mode**: `--quiet` flag (e.g., `auggie --print --quiet "your instruction"`) to tell the agent to only reply back with a final output. Ideal when you need to use the agent to provide structured data back without all the steps it took to get there. Provides a simple, clean response.


# Tool Permissions
Source: https://docs.augmentcode.com/cli/permissions

Control what tools Auggie CLI can execute with granular permission settings for security and compliance. Tool permissions configured will only work inside the CLI and not in the Augment code extension.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## About Tool Permissions

Auggie CLIs tool permission system provides fine-grained control over what actions the agent can perform in your environment. This security layer ensures that Auggie only executes approved operations, protecting your codebase and system from unintended changes.

Tool permissions are especially important when:

* Running Auggie in production environments
* Working with sensitive codebases
* Enforcing organizational security policies
* Using Auggie in automated workflows

## How Permissions Work

When Auggie attempts to use a tool, the permission system:

1. **Checks for matching rules** in your configuration
2. **Applies the first matching rule** based on tool name and optional patterns
3. **Rules are evaluated top-down** - first match wins
4. **Prompts for approval** when set to ask-user mode (interactive only)

### Permission Flow

```
Tool Request → Check Rules → Apply Permission → Execute/Deny → Log Decision
```

### Notes on Unmatched Tools

* Rules are evaluated in order from top to bottom
* The first matching rule determines the permission
* If no rules match, the CLI follows its implicit runtime behavior
* Configure explicit rules for all tools you want to control

## Configuration Files

Tool permissions are configured through `settings.json` files with clear precedence:

### File Locations

1. **User settings**: `~/.augment/settings.json`
   * Personal preferences that apply to all your projects
   * Ideal for your default security stance

2. **Project settings**: `<workspace>/.augment/settings.json`
   * Repository-specific rules shared with your team
   * Perfect for project-specific security requirements

<Note>Settings are merged with later files taking precedence. Project settings override user settings.</Note>

## Basic Configuration

### Creating Rules

Rules define permissions for specific tools. Each rule can specify:

* **Tool name** - The specific tool to control
* **Permission type** - `allow`, `deny`, or `ask-user`
* **Optional patterns** - For shell commands, use regex matching

### Basic Rule Structure

```json
{
  "tool-permissions": [
    { "tool-name": "launch-process", "permission": { "type": "deny" } },
    { "tool-name": "view", "permission": { "type": "allow" } }
  ]
}
```

### Allow List Configuration

Create an explicit allow list by only allowing specific tools:

```json
{
  "tool-permissions": [
    { "tool-name": "view", "permission": { "type": "allow" } },
    { "tool-name": "codebase-retrieval", "permission": { "type": "allow" } },
    { "tool-name": "grep-search", "permission": { "type": "allow" } },
    { "tool-name": "github-api", "permission": { "type": "allow" } }
  ]
}
```

<Note>This configuration explicitly allows only the listed tools. Tools not in this list will follow the CLI's implicit behavior.</Note>

### Block List Configuration

Create a block list by explicitly denying specific dangerous tools:

```json
{
  "tool-permissions": [
    { "tool-name": "remove-files", "permission": { "type": "deny" } },
    { "tool-name": "kill-process", "permission": { "type": "deny" } },
    { "tool-name": "launch-process", "shell-input-regex": "^(rm|sudo|shutdown|reboot)", "permission": { "type": "deny" } }
  ]
}
```

<Note>This configuration blocks specific dangerous operations. Tools not explicitly denied will follow the CLI's implicit behavior.</Note>

### Mix and Match Configuration

Combine allow, deny, and ask-user rules for fine-grained control:

```json
{
  "tool-permissions": [
    { "tool-name": "view", "permission": { "type": "allow" } },
    { "tool-name": "codebase-retrieval", "permission": { "type": "allow" } },
    { "tool-name": "grep-search", "permission": { "type": "allow" } },

    { "tool-name": "str-replace-editor", "permission": { "type": "ask-user" } },
    { "tool-name": "save-file", "permission": { "type": "ask-user" } },

    { "tool-name": "launch-process", "shell-input-regex": "^(npm test|npm run lint|git status|git diff)", "permission": { "type": "allow" } },
    { "tool-name": "launch-process", "shell-input-regex": "^(rm -rf|sudo|chmod 777)", "permission": { "type": "deny" } },
    { "tool-name": "launch-process", "permission": { "type": "ask-user" } },

    { "tool-name": "remove-files", "permission": { "type": "deny" } }
  ]
}
```

This configuration provides fine-grained control with different permission levels based on tool risk and usage patterns.

## Available Tools

### Process Management

| Tool             | Description                        |
| :--------------- | :--------------------------------- |
| `launch-process` | Execute shell commands and scripts |
| `read-process`   | Read output from running processes |
| `write-process`  | Send input to running processes    |
| `list-processes` | List all active processes          |
| `kill-process`   | Terminate running processes        |

### File Operations

| Tool                 | Description                         |
| :------------------- | :---------------------------------- |
| `view`               | Read file contents                  |
| `str-replace-editor` | Edit files with find/replace        |
| `save-file`          | Create or overwrite files           |
| `remove-files`       | Delete files from the filesystem    |
| `codebase-retrieval` | Search codebase with context engine |
| `grep-search`        | Search files with regex patterns    |

### External Services

| Tool         | Description                  |
| :----------- | :--------------------------- |
| `github-api` | GitHub API operations        |
| `linear`     | Linear issue tracking        |
| `notion`     | Notion workspace access      |
| `supabase`   | Supabase database operations |
| `web-search` | Web search queries           |
| `web-fetch`  | Fetch web page content       |

### MCP Server Tools

MCP tools follow the pattern `{tool-name}_{server-name}`:

* Example: `query_database-mcp`
* Truncated to 64 characters if longer
* Treated like any other tool for permissions

## Advanced Rules

### Shell Command Filtering

Control which shell commands can be executed using regex patterns:

```json
{
  "tool-permissions": [
    { "tool-name": "launch-process", "shell-input-regex": "^(ls|pwd|echo|cat|grep)\\s", "permission": { "type": "allow" } },
    { "tool-name": "launch-process", "permission": { "type": "deny" } }
  ]
}
```

This configuration:

1. Allows only safe commands (ls, pwd, echo, cat, grep)
2. Denies all other shell commands
3. Rules are evaluated in order - first match wins

### Event-Based Permissions

Control when permission checks occur:

```json
{
  "tool-permissions": [
    { "tool-name": "github-api", "event-type": "tool-response", "permission": { "type": "allow" } }
  ]
}
```

**Event types:**

* **`tool-call`** (default) - Check before tool execution
* **`tool-response`** - Check after execution but before returning results to agent

## Interactive Approval

When using `ask-user` mode in interactive sessions, Auggie displays approval prompts:

```
🔒 Tool Approval Required
─────────────────────────
Tool: launch-process
Command: npm install express

[A]llow once  [D]eny  [Always allow]  [Never allow]
```

### Keyboard Shortcuts

| Key   | Action                      |
| :---- | :-------------------------- |
| `A`   | Allow this specific request |
| `D`   | Deny this specific request  |
| `Y`   | Always allow this tool      |
| `N`   | Never allow this tool       |
| `Esc` | Cancel and deny request     |

<Note>In non-interactive mode (--print), ask-user permissions default to deny for security.</Note>

## Common Configurations

### Read-Only Mode

Allow only read operations, perfect for code review and analysis:

```json
{
  "tool-permissions": [
    { "tool-name": "view", "permission": { "type": "allow" } },
    { "tool-name": "codebase-retrieval", "permission": { "type": "allow" } },
    { "tool-name": "grep-search", "permission": { "type": "allow" } },
    { "tool-name": "web-search", "permission": { "type": "allow" } },
    { "tool-name": "web-fetch", "permission": { "type": "allow" } },
    { "tool-name": "str-replace-editor", "permission": { "type": "deny" } },
    { "tool-name": "save-file", "permission": { "type": "deny" } },
    { "tool-name": "remove-files", "permission": { "type": "deny" } },
    { "tool-name": "launch-process", "permission": { "type": "deny" } }
  ]
}
```

### Development Mode

Add safety guards for potentially dangerous operations:

```json
{
  "tool-permissions": [
    { "tool-name": "remove-files", "permission": { "type": "ask-user" } },
    {
      "tool-name": "launch-process",
      "shell-input-regex": "^(rm|sudo|chmod)\\s",
      "permission": { "type": "ask-user" }
    }
  ]
}
```

### CI/CD Pipeline

Restrictive settings for automated workflows:

```json
{
  "tool-permissions": [
    { "tool-name": "view", "permission": { "type": "allow" } },
    { "tool-name": "str-replace-editor", "permission": { "type": "allow" } },
    { "tool-name": "save-file", "permission": { "type": "allow" } },
    {
      "tool-name": "launch-process",
      "shell-input-regex": "^(npm test|npm run lint|jest)\\s",
      "permission": { "type": "allow" }
    },
    { "tool-name": "remove-files", "permission": { "type": "deny" } },
    { "tool-name": "launch-process", "permission": { "type": "deny" } }
  ]
}
```

## Custom Policies

### Webhook Validation

Use external services to validate tool requests:

```json
{
  "tool-permissions": [
    { "tool-name": "github-api", "permission": { "type": "webhook-policy", "webhook-url": "https://api.company.com/validate-tool" } }
  ]
}
```

The webhook receives:

```json
{
  "tool-name": "github-api",
  "event-type": "tool-call",
  "details": { /* tool-specific data */ },
  "timestamp": "2025-01-01T02:41:40.580Z"
}
```

Expected response:

```json
{
  "allow": true,
  "output": "Optional message to include in agent response"
}
```

### Script Validation

Use local scripts for complex validation logic:

```json
{
  "tool-permissions": [
    { "tool-name": "launch-process", "permission": { "type": "script-policy", "script": "/path/to/validate-command.sh" } }
  ]
}
```

## Best Practices

1. **Be Explicit**: Define clear rules for all tools you want to control
2. **Layer Settings**: Use user settings for defaults, project settings for team rules
3. **Test Configurations**: Verify permissions work as expected before automation
4. **Log Decisions**: Monitor which tools are being allowed/denied for audit trails
5. **Regular Reviews**: Periodically review and update permission rules
6. **Order Matters**: Remember that rules are evaluated top-down, first match wins

## Troubleshooting

**Permissions Not Working:**

* Check file locations and ensure settings.json is valid JSON
* Verify rule order - first matching rule wins
* Use `--augment-cache-dir` to specify custom settings directory

**Ask-User Mode in Automation:**

* Ask-user permissions automatically deny in non-interactive mode
* Use explicit allow/deny rules for automation scenarios
* Consider webhook or script policies for dynamic decisions

**MCP Tools Not Recognized:**

* Ensure MCP server name follows `{tool}_{server}` pattern
* Check for 64-character truncation on long names
* Verify MCP server is properly configured and running

## Security Considerations

* **Never commit sensitive webhook URLs** to version control
* **Use `.augment/settings.local.json`** for personal security overrides
* **Regularly audit** tool usage in production environments
* **Implement defense in depth** with multiple permission layers
* **Test permission changes** in isolated environments first

## Related Features

* [Authentication](/cli/setup-auggie/authentication) - Secure access to Auggie
* [Custom Rules](/cli/reference#custom-rules-files) - Project-specific guidelines
* [MCP Integrations](/cli/integrations) - External tool configuration
* [Automation](/cli/automation) - Using permissions in CI/CD


# CLI Flags and Options
Source: https://docs.augmentcode.com/cli/reference

A comprehensive reference for all command-line flags available in the Auggie CLI.

## CLI flags

| Command            | Description                                                              |
| :----------------- | :----------------------------------------------------------------------- |
| `auggie`           | Start Auggie in interactive mode                                         |
| `auggie --print`   | Output simple text for one instruction and exit                          |
| `auggie --quiet`   | Output only the final response for one instruction and exit              |
| `auggie --compact` | Output tool calls, results, and final response as one line each and exit |

### Input

| Command                                            | Description                                        |
| :------------------------------------------------- | :------------------------------------------------- |
| `auggie "Fix the typescript errors"`               | Provide an initial instruction in interactive mode |
| `auggie --print "Summarize the staged changes"`    | Provide an instruction and exit                    |
| `cat file \| auggie --print "Summarize this data"` | Pipe content through stdin                         |
| `auggie --print "Summarize this data" < file.txt`  | Provide input from a file                          |
| `auggie --instruction "Fix the errors"`            | Provide an initial instruction in interactive mode |
| `auggie --instruction-file /path/to/file.txt`      | Provide an instruction by file in interactive mode |

### Custom Commands

| Command                         | Description                                                                  |
| :------------------------------ | :--------------------------------------------------------------------------- |
| `auggie command <command-name>` | Execute a custom command from `.augment/commands/` or `~/.augment/commands/` |

Custom commands are reusable instructions stored as markdown files. They can be placed in:

* `~/.augment/commands/<name>.md` - Global commands (user-wide)
* `./.augment/commands/<name>.md` - Project commands (workspace-specific)
* `~/.claude/commands/<name>.md` - Claude Code user commands
* `./.claude/commands/<name>.md` - Claude Code workspace commands

Commands are resolved in order of precedence, with Auggie-specific locations taking priority over Claude Code locations.

**Examples:**

```sh
# Execute a custom deployment command
auggie command deploy-staging

# Execute a code review command
auggie command security-review

# List available commands (shown in help output)
auggie command help
```

See [Custom Commands](/cli/custom-commands) for detailed information on creating and managing custom commands.

### Sessions

| Command                          | Description                                       |
| :------------------------------- | :------------------------------------------------ |
| `auggie --continue` `(-c)`       | Resumes the previous conversation                 |
| `auggie --dont-save-session`     | Do not save the conversation to the local history |
| `auggie --delete-saved-sessions` | Delete all saved sessions from disk               |

### Configuration

| Command                                    | Description                                                               |
| :----------------------------------------- | :------------------------------------------------------------------------ |
| `auggie --workspace-root /path/to/project` | Specify the root of the workspace                                         |
| `auggie --rules /path/to/rules.md`         | Additional rules to append to workspace guidelines                        |
| `auggie --model "name"`                    | Select the model to use (accepts long or short names from the model list) |

### Models

List out available models and their short names to be passed into the `--model` flag

| Command                | Description                   |
| :--------------------- | :---------------------------- |
| `auggie --list-models` | List available models         |
| `auggie -lm`           | Shorthand for `--list-models` |

<Note>Tool permissions can be configured in settings.json files. See [Permissions](/cli/permissions) for detailed configuration.</Note>

### MCP and integrations

| Command                                 | Description                        |
| :-------------------------------------- | :--------------------------------- |
| `auggie --mcp-config {key: value}`      | MCP configuration as a JSON string |
| `auggie --mcp-config /path/to/mcp.json` | MCP configuration from a JSON file |

### Authentication

| Command                        | Description                                  |
| :----------------------------- | :------------------------------------------- |
| `auggie --login`               | Login to Augment and store the token locally |
| `auggie --logout`              | Remove the locally stored token              |
| `auggie --print-augment-token` | Print the locally stored token               |

### Additional commands

| Command            | Description  |
| :----------------- | :----------- |
| `auggie --help`    | Show help    |
| `auggie --version` | Show version |

## Environment Variables

| Variable               | Description          |
| ---------------------- | -------------------- |
| `AUGMENT_SESSION_AUTH` | Authentication JSON. |
| `AUGMENT_API_URL`      | Backend API endpoint |
| `AUGMENT_API_TOKEN`    | Authentication token |
| `GITHUB_API_TOKEN`     | GitHub API token     |

## Custom Rules Files

Auggie automatically loads custom rules and guidelines from several file locations to provide context-aware assistance. These files help Auggie understand your project's conventions, coding standards, and preferences.

### Supported Rules Files

Auggie looks for rules files in the following order of precedence:

1. **Custom rules file** (via `--rules` flag): `/path/to/custom-rules.md`
2. **CLAUDE.md**: Compatible with Claude Code and other AI tools
3. **AGENTS.md**: Compatible with Cursor and other AI development tools
4. **Workspace guidelines**: `.augment/guidelines.md` (legacy format)

### File Locations

**Workspace Root Files:**

* `CLAUDE.md` - Root-level rules file compatible with Claude Code
* `AGENTS.md` - Root-level rules file compatible with Cursor and other tools

**Augment Directory Files:**

* `.augment/guidelines.md` - Legacy workspace guidelines file
* `.augment/rules/` - Directory containing multiple rule files (IDE feature)

### Rules File Format

Rules files should be written in Markdown format with natural language instructions. Here's the recommended structure:

```markdown
# Project Guidelines

## Code Style
- Use TypeScript for all new JavaScript files
- Follow the existing naming conventions in the codebase
- Add JSDoc comments for all public functions and classes

## Architecture
- Follow the MVC pattern established in the codebase
- Place business logic in service classes
- Keep controllers thin and focused on request/response handling

## Testing
- Write unit tests for all new functions
- Maintain test coverage above 80%
- Use Jest for testing framework

## Dependencies
- Prefer built-in Node.js modules when possible
- Use npm for package management
- Pin exact versions in package.json for production dependencies
```

### Example Rules Files

**Basic Project Rules (CLAUDE.md):**

```markdown
# Development Guidelines

- Use semantic commit messages following conventional commits
- Run `npm run lint` before committing changes
- Update documentation when adding new features
- Follow the existing error handling patterns
- Use environment variables for configuration
```

**Framework-Specific Rules (AGENTS.md):**

```markdown
# React Project Guidelines

## Component Development
- Use functional components with hooks
- Implement proper TypeScript interfaces for props
- Follow the established folder structure in src/components/

## State Management
- Use React Context for global state
- Keep component state local when possible
- Use custom hooks for complex state logic

## Styling
- Use CSS modules for component styling
- Follow the design system tokens defined in src/styles/tokens.css
- Ensure responsive design for mobile and desktop
```

**Backend API Rules:**

```markdown
# API Development Guidelines

## Endpoint Design
- Follow RESTful conventions for URL structure
- Use appropriate HTTP status codes
- Include proper error messages in responses

## Database
- Use Prisma ORM for database operations
- Write database migrations for schema changes
- Include proper indexing for query performance

## Security
- Validate all input parameters
- Use JWT tokens for authentication
- Implement rate limiting on public endpoints
```

### Using Custom Rules Directory

You can specify a custom directory for Auggie's configuration files:

```bash
# Use custom directory instead of .augment
auggie --augment-cache-dir /path/to/custom-config

# This will look for rules in:
# /path/to/custom-config/guidelines.md
# /path/to/custom-config/rules/
```

### Best Practices for Rules Files

1. **Be Specific**: Provide clear, actionable guidelines rather than vague suggestions
2. **Use Examples**: Include code examples when describing patterns or conventions
3. **Keep Updated**: Regularly review and update rules as your project evolves
4. **Be Concise**: Focus on the most important guidelines to avoid overwhelming the AI
5. **Test Guidelines**: Verify that Auggie follows your rules by testing with sample requests

### Compatibility with Other Tools

The CLAUDE.md and AGENTS.md formats are designed to be compatible with other AI development tools:

* **Claude Code**: Uses CLAUDE.md for project-specific instructions
* **Cursor**: Supports AGENTS.md for AI assistant configuration
* **Other AI Tools**: Many tools are adopting these standard file formats

This ensures your rules work consistently across different AI development environments.


# Login and authentication
Source: https://docs.augmentcode.com/cli/setup-auggie/authentication

You will need an active account and valid session token to use Auggie CLI which you can get by following the instructions below.

## About authentication

Before you can use Auggie, you will need to login to create a session token that can be used by Auggie in both interactive and automation modes.

<Note>Augment authentication tokens are secrets and should be protected with the same level of security you'd use for any sensitive credential. Tokens are tied to the user who logged in, not to your team or enterprise account, so each user has a unique augment token.</Note>

## Logging in

You can login by running the following command and following the prompts.

```sh
auggie --login
```

## Logging out

You can logout by running the following command. This will remove the local token from your machine and you will need to login again to use Auggie.

```sh
auggie --logout
```

## Getting your token

For automation, you will need to provide your token each time you run Auggie. After you have logged in above, you can get your token by running the following command.

```sh
auggie --print-augment-token
```

## Using your token

After you have your token, you can pass it to Auggie through a number of methods depending on your use case and environment.

### Environment variables

You can set the `AUGMENT_SESSION_AUTH` environment variable to your token before running Auggie. Pass it before you run the command, add it to your environment, or add it to your shell's rc file to persist it.

```sh
AUGMENT_SESSION_AUTH='<token>'
```

### Token file

You can store the token as plaintext in a file and then use the `--token-file` flag to pass it to Auggie. We do not recommend checking your token into version control.

```sh
auggie --token-file /path/to/token
```

## Revoking your tokens

You can expire all the tokens for the current logged in user by running the following command. Using `--logout` will only remove the local token from your machine.

```sh
auggie --revoke-all-augment-tokens
```


# Install Auggie CLI
Source: https://docs.augmentcode.com/cli/setup-auggie/install-auggie-cli

Install Auggie to get agentic coding capabilities in your terminal, on your server, or anywhere your code runs.

```sh
npm install -g @augmentcode/auggie
```

# About installing Auggie

Installing Auggie CLI is easy and will take you less than a minute. You can install Auggie CLI directly from npm anywhere you can run Node 22 or later. Many systems do not ship with the latest version of Node.js, so you may need to upgrade Node to use Auggie.

Auggie is currently in beta and may not run on all environments and terminal configurations.

## System requirements

* [**Node.js 22+**](https://nodejs.org/en/download/)
* **Platforms**: MacOS, Windows WSL, Linux
* **Shells**: zsh, bash, fish

### Interactive mode

Using Auggie in interactive mode requires a terminal that supports ANSI escape codes. We recommend using Ghostty, iTerm2, MacOS Terminal, Windows Terminal, Alacritty, Kitty, and other modern terminals.

If you are connecting to your shell over SSH or through tmux you may need to adjust your terminal settings or configuration to enable proper color support, font rendering, and interactivity.


# Workspace context
Source: https://docs.augmentcode.com/cli/setup-auggie/workspace-context

Auggie will automatically index the current working directory or directory you specify to give Augment a full view of your system.

## About Workspace Context

Augment is powered by its deep understanding of your code. Your codebase will be automatically indexed when you run `auggie` from a git directory or you can specify a directory to index. If you run Auggie from a non-git directory, a temporary workspace will be created for you.

## Specifying a directory to index

To specify a directory other than the current working directory pass the target directory to the `--workspace-root` flag.

```sh
auggie --workspace-root /path/to/your/project
```

To learn more about what files are indexed and how to ignore files, see [Workspace indexing](/cli/setup-auggie/workspace-indexing).


# Index your workspace
Source: https://docs.augmentcode.com/cli/setup-auggie/workspace-indexing

When your workspace is indexed, Augment can provide tailored code suggestions and answers based on your unique codebase, best practices, coding patterns, and preferences. You can always control what files are indexed.

## Security and privacy

Augment stores your code securely and privately to enable our powerful context engine. We ensure code privacy through a proof-of-possession API and maintain strict internal data minimization principles. [Read more about our security](https://www.augmentcode.com/security).

## What gets indexed

Augment will index all the files in your workspace, except for the files that match patterns in your `.gitignore` file and the `.augmentignore` file. [Read more about Workspace Context](/cli/setup-auggie/workspace-context).

## Ignoring files with .augmentignore

The `.augmentignore` file is a list of file patterns that Augment will ignore when indexing your workspace. Create an `.augmentignore` file in the root of your workspace. You can use any glob pattern that is supported by the [gitignore](https://git-scm.com/docs/gitignore) file.

## Including files that are .gitignored

If you have a file or directory in your `.gitignore` that you want to be indexed, you can add it to your `.augmentignore` file using the `!` prefix.

For example, you may want your `node_modules` indexed to provide Augment with context about the dependencies in their project, but it is typically included in their `.gitignore`. Add `!node_modules` to your `.augmentignore` file.

<CodeGroup>
  ```bash .augmentignore
  # Include .gitignore excluded files with ! prefix
  !node_modules

  # Exclude other files with .gitignore syntax
  data/test.json
  ```

  ```bash .gitignore
  # Exclude dependencies
  node_modules

  # Exclude secrets
  .env

  # Exclude build artifacts
  out
  build
  ```
</CodeGroup>


# Introduction
Source: https://docs.augmentcode.com/introduction

Augment is the developer AI platform that helps you understand code, debug issues, and ship faster because it understands your codebase. Use Chat, Next Edit, and Code Completions to get more done.

export const NextEditIcon = () => <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16">
        <g fill="none" fill-rule="evenodd">
            <path fill="#868686" d="M11.007 7c.126 0 .225-.091.246-.232.288-1.812.611-2.241 2.522-2.515.14-.021.225-.12.225-.253 0-.126-.084-.225-.225-.246-1.918-.274-2.157-.681-2.522-2.536-.028-.127-.12-.218-.246-.218-.133 0-.232.091-.253.225-.288 1.848-.604 2.255-2.515 2.53-.14.027-.232.119-.232.245 0 .133.091.232.232.253 1.918.274 2.164.674 2.515 2.522.028.14.127.225.253.225Z" />
            <path fill="#A7A7A7" d="M14.006 8.8c.075 0 .135-.055.147-.14.173-1.087.367-1.344 1.514-1.508.084-.013.134-.072.134-.152 0-.076-.05-.135-.134-.148-1.151-.164-1.295-.408-1.514-1.521-.017-.076-.072-.131-.147-.131-.08 0-.14.055-.152.135-.173 1.109-.363 1.353-1.51 1.517-.084.017-.138.072-.138.148 0 .08.054.14.139.152 1.15.164 1.298.404 1.509 1.513.017.084.076.135.152.135Z" opacity=".6" />
            <g fill="#5f6368">
            <path fill-rule="nonzero" d="m5.983 4.612 4.22 4.22c.433.434.78.945 1.022 1.507l1.323 3.069a.908.908 0 0 1-1.192 1.192l-3.07-1.323a4.84 4.84 0 0 1-1.505-1.022L2.56 8.035l3.423-3.423Zm-.001 1.711L4.271 8.034l3.365 3.365c.27.271.582.497.922.67l.208.097 2.37 1.022-1.022-2.37a3.63 3.63 0 0 0-.61-.963l-.157-.167-3.365-3.365Zm-.706-2.417L1.854 7.327l-.096-.104a2.42 2.42 0 0 1 3.518-3.317Z" />
            <path d="m11.678 11.388.87 2.02a.908.908 0 0 1-1.192 1.192l-2.02-.87 2.342-2.342ZM5.303 3.933l4.9 4.9c.084.083.164.17.242.26L7.04 12.497a4.84 4.84 0 0 1-.26-.242l-4.9-4.9a2.42 2.42 0 0 1 3.422-3.422Z" />
            </g>
        </g>
    </svg>;

export const CodeIcon = () => <svg xmlns="http://www.w3.org/2000/svg" height="28px" viewBox="0 -960 960 960" width="28px" fill="#5f6368">
    <path d="M336-240 96-480l240-240 51 51-189 189 189 189-51 51Zm288 0-51-51 189-189-189-189 51-51 240 240-240 240Z" />
  </svg>;

export const ChatIcon = () => <svg xmlns="http://www.w3.org/2000/svg" height="28px" viewBox="0 -960 960 960" width="28px" fill="#5f6368">
    <path d="M864-96 720-240H360q-29.7 0-50.85-21.15Q288-282.3 288-312v-48h384q29.7 0 50.85-21.15Q744-402.3 744-432v-240h48q29.7 0 50.85 21.15Q864-629.7 864-600v504ZM168-462l42-42h390v-288H168v330ZM96-288v-504q0-29.7 21.15-50.85Q138.3-864 168-864h432q29.7 0 50.85 21.15Q672-821.7 672-792v288q0 29.7-21.15 50.85Q629.7-432 600-432H240L96-288Zm72-216v-288 288Z" />
  </svg>;

<img className="block rounded-xl" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-hero-sm.png?maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a23b4796a315d6187643db77d4616ba1" alt="Augment Code" width="800" height="467" data-path="images/augment-hero-sm.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-hero-sm.png?w=280&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c6ae0136d0a48bc099d8df2cb67a0616 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-hero-sm.png?w=560&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=dce80fb182825b50a34af82b4c8ca3f0 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-hero-sm.png?w=840&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4cc08a84611f2e095ae7b7e8f0d48095 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-hero-sm.png?w=1100&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d42b136e75a8329632bf395db3e5ce87 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-hero-sm.png?w=1650&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=76955c1a5d212d578d4a0f45d53591de 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-hero-sm.png?w=2500&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5a8349949c679dea3fd8f0c1eeb91430 2500w" data-optimize="true" data-opv="2" />

## Get started in minutes

Augment works with your favorite IDE and your favorite programming language. Download the extension, sign in, and get coding.

<CardGroup cols={3}>
  <Card href="/setup-augment/install-visual-studio-code">
    <img className="w-12 h-12" src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b6d0dafb62816d87fb9996ea8af5e25e" alt="Visual Studio Code" width="64" height="64" data-path="images/vscode-icon.svg" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=280&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=8a8f401bdacbb6a397e28030e0610e28 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=560&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3cb81100f08c3223e70740ea3e20d7dd 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=840&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=f71758a22683cdc9e08bf703b1974b08 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=1100&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=86aeb522022e61b3f70f0ebec5d586ec 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=1650&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=cfbe41cb1bdf9c79bac51c7844be89b6 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=2500&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=48b8399d625178d62d883889647b7d91 2500w" data-optimize="true" data-opv="2" />

    <h2 className="pt-4 font-semibold text-base text-gray-800 dark:text-white">
      Visual Studio Code
    </h2>

    <p>
      Get completions, chat, and instructions in your favorite open source
      editor.
    </p>
  </Card>

  <Card className="bg-red" href="/setup-augment/install-jetbrains-ides">
    <img className="w-12 h-12" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4cf0e1e9968e1dd6ef465d292aa5b507" alt="JetBrains IDEs" width="64" height="64" data-path="images/jetbrains-icon.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=280&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9b4f573392cdff10ac1b019b5aa576f3 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=560&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1aeb7a8a9645688cff751bf264f6d5bb 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=840&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4f4a505397fbe4100c9dbf16c0597793 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=1100&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e7f21219990815a15d018e71e58fa7eb 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=1650&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4538c670242c92afa3dc0f9b6b37e4bf 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=2500&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=562de59a3e122c81c162bb6d0dd82a1a 2500w" data-optimize="true" data-opv="2" />

    <h2 className="pt-4 font-semibold text-base text-gray-800 dark:text-white">
      JetBrains IDEs
    </h2>

    <p>
      Completions are available for all JetBrains IDEs, like WebStorm, PyCharm,
      and IntelliJ.
    </p>
  </Card>

  <Card className="bg-red" href="/vim/setup-augment/install-vim-neovim">
    <img className="w-12 h-12" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f8bcad890f46810d3554bd3902d2c810" alt="Vim and Neovim" width="24" height="24" data-path="images/neovim-logo.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=280&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e9abfadd0177662c13b6ad717515ef80 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=560&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9380e4ad3fb7293545668ab44d1ac10a 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=840&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e12d0db7ed0199e1bdb982b14acc7fe9 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=1100&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e4f30e851dd968fbeec2d469bc0ec889 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=1650&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8e728c1b6f1b98f01cc8a32a3df249c9 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=2500&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8dd8e9292c4ecc9ecf0ffeb5d3c202b0 2500w" data-optimize="true" data-opv="2" />

    <h2 className="pt-4 font-semibold text-base text-gray-800 dark:text-white">
      Vim and Neovim
    </h2>

    <p>
      Get completions and chat in your favorite text editor.
    </p>
  </Card>
</CardGroup>

## Learn more

Get up to speed, stay in the flow, and get more done. Chat, Next Edit, and Code Completions will change the way you build software.

<CardGroup cols={3}>
  <Card title="Chat" icon={<ChatIcon />} href="/using-augment/chat">
    Never get stuck getting started again. Chat will help you get up to speed on
    unfamiliar code.
  </Card>

  <Card title="Next Edit" icon={<NextEditIcon />} href="/using-augment/next-edit">
    Keep moving through your tasks by guiding you step-by-step through complex or repetitive changes.
  </Card>

  <Card title="Code Completions" icon={<CodeIcon />} href="/using-augment/completions">
    Intelligent code suggestions that knows your codebase right at your
    fingertips.
  </Card>
</CardGroup>


# Agent Integrations
Source: https://docs.augmentcode.com/jetbrains/setup-augment/agent-integrations

Configure integrations for Augment Agent to access external services like GitHub, Linear, Jira, Confluence, and Notion.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const GleanLogo = () => <svg width="24" height="24" viewBox="0 0 16 16" fill="none" xmlns="http://www.w3.org/2000/svg">
  <path fill-rule="evenodd" clip-rule="evenodd" d="M8.95113 2.67649L10.2775 1L11.887 2.24179L10.5704 3.906C11.25 4.70862 11.6591 5.74239 11.6591 6.87053C11.6591 9.42425 9.56277 11.4945 6.9768 11.4945C4.39084 11.4945 2.29451 9.42425 2.29451 6.87053C2.29451 4.31677 4.39084 2.24655 6.9768 2.24655C7.68222 2.24655 8.35119 2.4006 8.95113 2.67649ZM6.9768 9.50853C5.50146 9.50853 4.30546 8.32747 4.30546 6.87053C4.30546 5.41358 5.50146 4.23245 6.9768 4.23245C8.45215 4.23245 9.64814 5.41358 9.64814 6.87053C9.64814 8.32747 8.45215 9.50853 6.9768 9.50853ZM11.7135 10.8261C11.5975 10.9618 11.4753 11.0913 11.3477 11.2173C11.2202 11.3424 11.0873 11.4622 10.949 11.5758C10.8116 11.6894 10.6689 11.7969 10.5208 11.8982C10.3736 11.9995 10.2211 12.0955 10.065 12.1837C9.90978 12.2726 9.75012 12.3537 9.58684 12.4286C9.42448 12.5034 9.25856 12.5712 9.08906 12.6311C8.92046 12.6919 8.74919 12.7448 8.57434 12.7898C8.40217 12.8365 8.22645 12.8743 8.04892 12.9043C7.87319 12.9351 7.69478 12.958 7.51459 12.973C7.33706 12.988 7.15776 12.9959 6.97667 12.9959C6.79558 12.9959 6.61628 12.988 6.43876 12.973C6.25856 12.958 6.08016 12.9351 5.90441 12.9043C5.7269 12.8743 5.55116 12.8365 5.379 12.7898L4.85357 14.726C5.08194 14.7868 5.31565 14.838 5.55206 14.8784C5.78488 14.919 6.02217 14.9498 6.26213 14.9692C6.49763 14.9895 6.73582 15 6.97667 15C7.21753 15 7.4557 14.9895 7.69121 14.9692C7.93117 14.9498 8.16756 14.919 8.40129 14.8784C8.63768 14.838 8.87051 14.7868 9.09977 14.726C9.33171 14.6662 9.56007 14.5957 9.7831 14.5147C10.0088 14.4345 10.2291 14.3446 10.445 14.2451C10.6617 14.1455 10.8741 14.0372 11.0802 13.92C11.2871 13.802 11.4887 13.6751 11.684 13.5394C11.8803 13.4047 12.0704 13.2619 12.2532 13.1104C12.437 12.9589 12.6136 12.8003 12.7822 12.6338C12.9517 12.4673 13.1131 12.2946 13.2675 12.1141C13.4218 11.9343 13.5681 11.7467 13.7055 11.5538L12.0435 10.4041C11.9401 10.5495 11.8295 10.6905 11.7135 10.8261Z" fill="currentColor" />
</svg>;

export const ConfluenceLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M2.43703 10.7785C2.30998 10.978 2.16478 11.2137 2.05588 11.3951C1.94698 11.5764 2.00143 11.8121 2.18293 11.921L4.66948 13.4442C4.85098 13.553 5.08695 13.4986 5.19585 13.3173C5.2866 13.1541 5.41365 12.9365 5.55885 12.7007C6.53895 11.0868 7.5372 11.2681 9.3159 12.1204L11.7843 13.281C11.9839 13.3717 12.2017 13.281 12.2925 13.0997L13.4722 10.4339C13.563 10.2526 13.4722 10.0169 13.2907 9.92619C12.7644 9.69044 11.7298 9.20084 10.8223 8.74749C7.44645 7.13354 4.59689 7.24234 2.43703 10.7785Z" fill="currentColor" />
  <path d="M13.563 4.72157C13.69 4.52209 13.8352 4.28635 13.9441 4.105C14.053 3.92366 13.9985 3.68791 13.817 3.57911L11.3305 2.05583C11.149 1.94702 10.913 2.00143 10.8041 2.18277C10.7134 2.34598 10.5863 2.56359 10.4411 2.79934C9.461 4.41329 8.46275 4.23194 6.68405 3.37963L4.21563 2.21904C4.01598 2.12837 3.79818 2.21904 3.70743 2.40038L2.52767 5.0661C2.43692 5.24745 2.52767 5.4832 2.70917 5.5739C3.23552 5.80965 4.27007 6.29925 5.1776 6.7526C8.53535 8.34845 11.3849 8.25775 13.563 4.72157Z" fill="currentColor" />
</svg>;

export const JiraLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg"><path fill-rule="evenodd" clip-rule="evenodd" d="M13.5028 2H7.7257C7.7257 3.44 8.8914 4.60571 10.3314 4.60571H11.3942V5.6343C11.3942 7.0743 12.5599 8.24 14 8.24V2.49714C14 2.22285 13.7771 2 13.5028 2ZM10.6399 4.88H4.86279C4.86279 6.32 6.0285 7.4857 7.4685 7.4857H8.53135V8.5143C8.53135 9.9543 9.69705 11.12 11.137 11.12V5.37715C11.137 5.10285 10.9142 4.88 10.6399 4.88ZM2 7.75995H7.7771C8.0514 7.75995 8.27425 7.9828 8.27425 8.2571V13.9999C6.83425 13.9999 5.66855 12.8342 5.66855 11.3942V10.3656H4.6057C3.16571 10.3656 2 9.19995 2 7.75995Z" fill="currentColor" />
</svg>;

export const NotionLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path d="M3.47498 3.32462C3.92288 3.68848 4.0909 3.66071 4.93192 3.60461L12.8609 3.12851C13.029 3.12851 12.8892 2.96075 12.8332 2.93286L11.5163 1.98091C11.264 1.78502 10.9278 1.56068 10.2835 1.6168L2.60594 2.17678C2.32595 2.20454 2.27001 2.34453 2.38153 2.45676L3.47498 3.32462ZM3.95103 5.17244V13.5151C3.95103 13.9634 4.17508 14.1312 4.67938 14.1035L13.3933 13.5992C13.8978 13.5715 13.954 13.263 13.954 12.8989V4.61222C13.954 4.24858 13.8142 4.05248 13.5053 4.08047L4.39915 4.61222C4.06311 4.64046 3.95103 4.80855 3.95103 5.17244ZM12.5534 5.61996C12.6093 5.87218 12.5534 6.12417 12.3007 6.15251L11.8808 6.23616V12.3952C11.5163 12.5911 11.1801 12.7031 10.9 12.7031C10.4516 12.7031 10.3392 12.5631 10.0033 12.1433L7.257 7.83198V12.0034L8.12602 12.1995C8.12602 12.1995 8.12602 12.7031 7.4249 12.7031L5.49203 12.8152C5.43588 12.7031 5.49203 12.4235 5.68808 12.3673L6.19248 12.2276V6.71226L5.49215 6.65615C5.43599 6.40392 5.57587 6.04029 5.96841 6.01205L8.04196 5.87229L10.9 10.2398V6.37615L10.1713 6.29251C10.1154 5.98418 10.3392 5.76029 10.6195 5.73252L12.5534 5.61996ZM1.96131 1.42092L9.94726 0.832827C10.928 0.748715 11.1803 0.805058 11.7967 1.25281L14.3458 3.04451C14.7665 3.35262 14.9067 3.4365 14.9067 3.77237V13.5992C14.9067 14.215 14.6823 14.5793 13.8979 14.635L4.6239 15.1951C4.03509 15.2231 3.75485 15.1392 3.4465 14.747L1.56922 12.3113C1.23284 11.863 1.09296 11.5276 1.09296 11.1351V2.40043C1.09296 1.89679 1.31736 1.47669 1.96131 1.42092Z" fill="currentColor" />
  </svg>;

export const LinearLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path d="M1.17156 9.61319C1.14041 9.4804 1.2986 9.39676 1.39505 9.49321L6.50679 14.6049C6.60323 14.7014 6.5196 14.8596 6.38681 14.8284C3.80721 14.2233 1.77669 12.1928 1.17156 9.61319ZM1.00026 7.56447C0.997795 7.60413 1.01271 7.64286 1.0408 7.67096L8.32904 14.9592C8.35714 14.9873 8.39586 15.0022 8.43553 14.9997C8.76721 14.9791 9.09266 14.9353 9.41026 14.8701C9.51729 14.8481 9.55448 14.7166 9.47721 14.6394L1.36063 6.52279C1.28337 6.44552 1.15187 6.48271 1.12989 6.58974C1.06466 6.90734 1.02092 7.23278 1.00026 7.56447ZM1.58953 5.15875C1.56622 5.21109 1.57809 5.27224 1.6186 5.31275L10.6872 14.3814C10.7278 14.4219 10.7889 14.4338 10.8412 14.4105C11.0913 14.2991 11.3336 14.1735 11.5672 14.0347C11.6445 13.9888 11.6564 13.8826 11.5929 13.819L2.18099 4.40714C2.11742 4.34356 2.01121 4.35549 1.96529 4.43278C1.8265 4.66636 1.70091 4.9087 1.58953 5.15875ZM2.77222 3.53036C2.7204 3.47854 2.7172 3.39544 2.76602 3.34079C4.04913 1.9043 5.9156 1 7.99327 1C11.863 1 15 4.13702 15 8.00673C15 10.0844 14.0957 11.9509 12.6592 13.234C12.6046 13.2828 12.5215 13.2796 12.4696 13.2278L2.77222 3.53036Z" fill="currentColor" />
  </svg>;

export const GitHubLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path fill-rule="evenodd" clip-rule="evenodd" d="M7.49933 0.25C3.49635 0.25 0.25 3.49593 0.25 7.50024C0.25 10.703 2.32715 13.4206 5.2081 14.3797C5.57084 14.446 5.70302 14.2222 5.70302 14.0299C5.70302 13.8576 5.69679 13.4019 5.69323 12.797C3.67661 13.235 3.25112 11.825 3.25112 11.825C2.92132 10.9874 2.44599 10.7644 2.44599 10.7644C1.78773 10.3149 2.49584 10.3238 2.49584 10.3238C3.22353 10.375 3.60629 11.0711 3.60629 11.0711C4.25298 12.1788 5.30335 11.8588 5.71638 11.6732C5.78225 11.205 5.96962 10.8854 6.17658 10.7043C4.56675 10.5209 2.87415 9.89918 2.87415 7.12104C2.87415 6.32925 3.15677 5.68257 3.62053 5.17563C3.54576 4.99226 3.29697 4.25521 3.69174 3.25691C3.69174 3.25691 4.30015 3.06196 5.68522 3.99973C6.26337 3.83906 6.8838 3.75895 7.50022 3.75583C8.1162 3.75895 8.73619 3.83906 9.31523 3.99973C10.6994 3.06196 11.3069 3.25691 11.3069 3.25691C11.7026 4.25521 11.4538 4.99226 11.3795 5.17563C11.8441 5.68257 12.1245 6.32925 12.1245 7.12104C12.1245 9.9063 10.4292 10.5192 8.81452 10.6985C9.07444 10.9224 9.30633 11.3648 9.30633 12.0413C9.30633 13.0102 9.29742 13.7922 9.29742 14.0299C9.29742 14.2239 9.42828 14.4496 9.79591 14.3788C12.6746 13.4179 14.75 10.7025 14.75 7.50024C14.75 3.49593 11.5036 0.25 7.49933 0.25Z" fill="currentColor" />
  </svg>;

## About Agent Integrations

Augment Agent can access external services through integrations to add additional context to your requests and take actions on your behalf. These integrations allow Augment Agent to seamlessly work with your development tools without leaving your editor.

Once set up, Augment Agent will automatically use the appropriate integration based on your request context. Or, you can always mention the service in your request to use the integration.

## Setting Up Integrations

To set up integrations with Augment Agent in JetBrains IDEs, follow these steps:

1. Click the Augment icon in the bottom right of your IDE and select <Command text="Tools Settings" />
2. Click "Connect" for the integration you want to set up

<img className="block rounded-xl" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=89a56ce1b2adfceeff53aa5c2c7e1e3d" alt="Set up integrations in the settings page" width="1096" height="598" data-path="images/integration-settings.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=280&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=340403281e17bb92431e2d8256147913 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=560&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5181e8e7a090238dc17c4bf037af62a4 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=840&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f3549289d4e1246092e524dbd7a012fc 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=1100&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=edf707f8b5706d828f47005b842d574e 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=1650&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a17cb3a8b511caeb927cd707398e4c28 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=2500&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8863d6e3a97b999eada3abab0279cc82 2500w" data-optimize="true" data-opv="2" />

You'll be redirected to authorize the integration with the appropriate service. After authorization, the integration will be available for use with Augment Agent.

## Easy MCP Integrations

> **New:** Easy MCP launched ONLY July 30, 2025, providing one-click access to popular developer tools.

Easy MCP transforms complex MCP server setup into a single click. Available integrations include:

* **CircleCI** - Build logs, test insights, and flaky-test detection
* **MongoDB** - Data exploration, database management, and context-aware code generation
* **Redis** - Keyspace introspection, TTL audits, and migration helpers

For detailed setup instructions and examples, see [Configure MCP servers](/jetbrains/setup-augment/mcp).

## Native Integrations

## <div className="flex items-center gap-2"><div className="w-6 h-6"><GitHubLogo /></div> GitHub Integration</div>

Add additional context to your requests and take actions. Pull in information from a GitHub Issue, make the changes to your code (or have Agent do it for you), and open a Pull Request all without leaving your editor.

### Examples

* "Implement Issue #123 and open up a pull request"
* "Find all issues assigned to me"
* "Check the CI status of my latest commit"

For authorization details, see [GitHub documentation](https://docs.github.com/en/apps/using-github-apps/installing-a-github-app-from-a-third-party).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><LinearLogo /></div> Linear Integration</div>

Read, update, comment on, and resolve your Linear issues within your IDE.

### Examples

* "Fix TES-1"
* "Create Linear tickets for these TODOs"
* "Help me triage these new bug reports"

For authorization details, see [Linear documentation](https://linear.app/docs/third-party-application-approvals).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><JiraLogo /></div> Jira Integration</div>

Work on your Jira issues, create new tickets, and update existing ones.

### Examples

* "Show me all my assigned Jira tickets"
* "Create a Jira ticket for this bug"
* "Create a PR to fix SOF-123"
* "Update the status of PROJ-123 to 'In Progress'"

For authorization details, see [Jira documentation](https://support.atlassian.com/jira-software-cloud/docs/allow-oauth-access/).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><ConfluenceLogo /></div> Confluence Integration</div>

Query existing documentation or update pages directly from your IDE. Ensure your team's knowledge base stays current without any context switching.

### Examples

* "Summarize our Confluence page on microservice architecture"
* "Find information about our release process in Confluence"
* "Update our onboarding docs to explain how we use Bazel"

For authorization details, see [Confluence documentation](https://developer.atlassian.com/cloud/confluence/oauth-2-3lo-apps/).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><NotionLogo /></div> Notion Integration</div>

Search and retrieve information from your team's knowledge base - access documentation, meeting notes, and project specifications. This integration is currently READ-ONLY.

### Examples

* "Find Notion pages about our API documentation"
* "Show me the technical specs for the payment system"
* "What outstanding tasks are left from yesterday's team meeting?"

For authorization details, see [Notion documentation](https://www.notion.so/help/add-and-manage-connections-with-the-api#install-from-a-developer).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><GleanLogo /></div> Glean Integration</div>

> **Note:** The Glean integration is in early access and thus is a little different from other integrations.
>
> * It is currently only available to enterprise customers.
> * It does not appear in the list of integrations in the settings panel.

The Glean integration lets the agent retrieve information from your team's internal data sources leveraging Glean's powerful search engine.

**To Enable the Glean Integration:** You'll need to be have administrator access to Augment and Glean. Follow the instructions on [https://app.augmentcode.com/dashboard/glean](https://app.augmentcode.com/dashboard/glean) and your agent will be ready to use Glean!

### Examples

* "Search Glean for past related incidents and how they were resolved"
* "Search Glean for why we're migrating to a new payment processor"

## Next Steps

* [Configure additional tools with Easy MCP or advanced MCP setup](/jetbrains/setup-augment/mcp)
* Explore one-click integrations for CircleCI, MongoDB, and Redis through Easy MCP


# Install Augment for JetBrains IDEs
Source: https://docs.augmentcode.com/jetbrains/setup-augment/install-jetbrains-ides

Are you ready for your new superpowers? Augment in JetBrains IDEs gives you powerful code completions integrated into your favorite text editor.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const ExternalLink = ({text, href}) => <a href={href} rel="noopener noreferrer">
    {text}
  </a>;

export const JetbrainsLogo = () => <svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 64 64">
    <defs>
      <linearGradient id="linear-gradient" x1=".8" y1="3.3" x2="62.6" y2="64.2" gradientTransform="translate(0 66) scale(1 -1)" gradientUnits="userSpaceOnUse">
        <stop offset="0" stop-color="#ff9419" />
        <stop offset=".4" stop-color="#ff021d" />
        <stop offset="1" stop-color="#e600ff" />
      </linearGradient>
    </defs>
    <path fill="url(#linear-gradient)" d="M20.3,3.7L3.7,20.3c-2.3,2.3-3.7,5.5-3.7,8.8v29.8c0,2.8,2.2,5,5,5h29.8c3.3,0,6.5-1.3,8.8-3.7l16.7-16.7c2.3-2.3,3.7-5.5,3.7-8.8V5c0-2.8-2.2-5-5-5h-29.8c-3.3,0-6.5,1.3-8.8,3.7Z" />
    <path fill="#000" d="M48,16H8v40h40V16Z" />
    <path fill="#fff" d="M30,47H13v4h17v-4Z" />
  </svg>;

<Info>
  Augment requires version `2024.3` or above for all JetBrains IDEs. [See
  JetBrains documentation](https://www.jetbrains.com/help/) on how to update
  your IDE.
</Info>

<CardGroup cols={1}>
  <Card title="Get the Augment Plugin" href="https://plugins.jetbrains.com/plugin/24072-augment" icon={<JetbrainsLogo />} horizontal>
    Install Augment for JetBrains IDEs
  </Card>
</CardGroup>

## About Installation

Installing <ExternalLink text="Augment for JetBrains IDEs" href="https://plugins.jetbrains.com/plugin/24072-augment" /> is easy and will take you less than a minute. Augment is compatible with all JetBrains IDEs, including WebStorm, PyCharm, and IntelliJ. You can find the Augment plugin in the JetBrains Marketplace and install it following the instructions below.

<img className="block rounded-xl" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-plugin.png?maxW=1652&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7cc6abf56c6e141717a4960d07517ba9" alt="Augment plugin in JetBrains Marketplace" width="1652" height="614" data-path="images/jetbrains-plugin.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-plugin.png?w=280&maxW=1652&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4e137bd2a6a1a64c9149c5d21a7bbc91 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-plugin.png?w=560&maxW=1652&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d97f8021055e88ec55d064551cf24c18 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-plugin.png?w=840&maxW=1652&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c33f78b9b824a87d1a441e1290d0bb31 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-plugin.png?w=1100&maxW=1652&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7e9f04745a8e03291e51f5529af3c866 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-plugin.png?w=1650&maxW=1652&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7520cee810f2f2d6968e165b187eb6e5 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-plugin.png?w=2500&maxW=1652&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=01322fd5f71948c01fd6d37b314a73fc 2500w" data-optimize="true" data-opv="2" />

## Installing Augment for JetBrains IDEs

<Note>
  For these instructions we'll use *JetBrains IntelliJ* as an example, anywhere
  you see *IntelliJ* replace the name of the JetBrains IDE you're using.

  In the case of Android Studio, which is based on IntelliJ, please ensure that your installation
  uses a runtime with JCEF. Go to <Command text="Help > Find Action" />, type <Command text="Choose Boot Java Runtime for the IDE" />
  and press <Keyboard shortcut="Enter" />. Ensure the current runtime ends with `-jcef`; if not, select one **with JCEF** from the options
  below.
</Note>

<Steps>
  <Step title="Make sure you have the latest version of your IDE installed">
    You can download the latest version of JetBrains IDEs from the <ExternalLink text="JetBrains" href="https://www.jetbrains.com/ides/#choose-your-ide" />
    website. If you already have IntelliJ installed, you can update to the
    latest version by going to{" "}
    <Command text="IntelliJ IDEA > Check for Updates..." />.
  </Step>

  <Step title="Open the Plugins settings in your IDE">
    From the menu bar, go to <Command text="IntelliJ IDEA > Settings..." />, or
    use the keyboard shortcut <Keyboard shortcut="Cmd/Ctrl ," /> to open the
    Settings window. Select <Command text="Plugins" /> from the sidebar.
  </Step>

  <Step title="Search for Augment in the marketplace">
    Using the search bar in the Plugins panel, search for{" "}
    <Command text="Augment" />.
  </Step>

  <Step title="Install the extension">
    Click <Command text="Install" /> to install the extension. Then click{" "}
    <Command text="OK" /> to close the Settings window.
  </Step>

  <Step title="Sign into Augment and get coding">
    Sign in to by clicking <Command text="Sign in to Augment" /> in the Augment
    panel. If you do not see the Augment panel, use the shortcut{" "}
    <Keyboard shortcut="Cmd/Ctrl L" /> or click the Augment icon{" "}
    <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c45fb0199a88c329cbfad5e2d0c225a1" className="inline h-3 p-0 m-0" width="18" height="12" data-path="images/augment-icon-simple.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=280&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8b6cc675b3b75b7896bd431f64a092a0 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=560&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4c6ce1c701082b4f77e38ab0328a9f30 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=840&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8b8a4c9d542987cc6b15dae04d718a95 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=1100&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0d07791cb30b119aa46e3b4d6006628c 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=1650&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9a24403942c20bdfc300b06276e49f56 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=2500&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f6bb21ac056e042477613841f39510b4 2500w" data-optimize="true" data-opv="2" /> in the side bar of your IDE. See more details in [Sign
    In](/setup-augment/sign-in).
  </Step>
</Steps>

## Installing Beta versions of Augment for JetBrains IDEs

In order to get a specific bug fix or feature, sometimes you may need to *temporarily* install a beta version of Augment for JetBrains IDEs.
To do this, follow the steps below:

<Steps>
  <Step title="Download an archive of the beta version">
    You can download the latest beta version of Augment from <ExternalLink text="JetBrains Marketplace" href="https://plugins.jetbrains.com/plugin/24072-augment/versions/beta?noRedirect=true" />
    website. Please click <Command text="Download" /> on the latest version and save the archive to disk.
  </Step>

  <Step title="Open the Plugins settings in your IDE">
    From the menu bar, go to <Command text="IntelliJ IDEA > Settings..." />, or
    use the keyboard shortcut <Keyboard shortcut="Cmd/Ctrl ," /> to open the
    Settings window. Select <Command text="Plugins" /> from the sidebar.
  </Step>

  <Step title="Install Augment from the downloaded archive">
    Click on the gear icon next to <Command text="Installed" /> tab and click <Command text="Install plugin from disk..." />.
    Select the archive you downloaded in the previous step and click <Command text="OK" />.
  </Step>
</Steps>


# Keyboard Shortcuts for JetBrains IDEs
Source: https://docs.augmentcode.com/jetbrains/setup-augment/jetbrains-keyboard-shortcuts

Augment integrates with your IDE to provide keyboard shortcuts for common actions. Use these shortcuts to quickly accept suggestions, write code, and navigate your codebase.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About keyboard shortcuts

Augment is deeply integrated into your IDE and utilizes many of the standard keyboard shortcuts you are already familiar with. These shortcuts allow you to quickly accept suggestions, write code, and navigate your codebase. We also suggest updating a few keyboard shortcuts to make working with code suggestions even easier.

<Tabs>
  <Tab title="MacOS">
    To update keyboard shortcuts, use one of the following:

    | Method   | Action                                                         |
    | :------- | :------------------------------------------------------------- |
    | Keyboard | <Keyboard shortcut="Cmd ," /> select <Command text="Keymap" /> |
    | Menu bar | <Command text="IntelliJ IDEA > Settings > Keymap" />           |

    ## General

    | Action             | Default shortcut                     |
    | :----------------- | :----------------------------------- |
    | Open Augment panel | <Keyboard shortcut="Cmd Option I" /> |

    ## Chat

    | Action                   | Default shortcut                     |
    | :----------------------- | :----------------------------------- |
    | Focus or open Chat panel | <Keyboard shortcut="Cmd Option I" /> |

    ## Completions

    | Action                       | Default shortcut                     |
    | :--------------------------- | :----------------------------------- |
    | Accept entire suggestion     | <Keyboard shortcut="Tab" />          |
    | Accept word-by-word          | <Keyboard shortcut="Option Right" /> |
    | Reject suggestion            | <Keyboard shortcut="Esc" />          |
    | Toggle automatic completions | <Keyboard shortcut="Cmd Option 9" /> |
  </Tab>

  <Tab title="Windows/Linux">
    To update keyboard shortcuts, use one of the following:

    | Method   | Action                                                               |
    | :------- | :------------------------------------------------------------------- |
    | Keyboard | <Keyboard shortcut="Ctrl ," /> then select <Command text="Keymap" /> |
    | Menu bar | <Command text="File > Settings > Keymap" />                          |

    ## General

    | Action             | Default shortcut                   |
    | :----------------- | :--------------------------------- |
    | Open Augment panel | <Keyboard shortcut="Ctrl Alt I" /> |

    ## Chat

    | Action                   | Default shortcut                   |
    | :----------------------- | :--------------------------------- |
    | Focus or open Chat panel | <Keyboard shortcut="Ctrl Alt I" /> |

    ## Completions

    | Action                       | Default shortcut                   |
    | :--------------------------- | :--------------------------------- |
    | Accept entire suggestion     | <Keyboard shortcut="Tab" />        |
    | Accept word-by-word          | <Keyboard shortcut="Ctrl Right" /> |
    | Reject suggestion            | <Keyboard shortcut="Esc" />        |
    | Toggle automatic completions | <Keyboard shortcut="Ctrl Alt 9" /> |
  </Tab>
</Tabs>


# Setup Model Context Protocol servers
Source: https://docs.augmentcode.com/jetbrains/setup-augment/mcp

Use Model Context Protocol (MCP) servers with Augment to expand Augment's capabilities with external tools and data sources.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## About Model Context Protocol servers

Augment Agent can utilize external integrations through Model Context Protocol (MCP) to access external systems for information and integrate tools to take actions. MCP is an open protocol that provides a standardized way to connect AI models to different data sources and tools. MCP servers can be used to access local or remote databases, run automated browser testing, send messages to Slack or even play music on Spotify.

## Easy MCP: One-Click Integrations

> **New:** Easy MCP launched on July 30, 2025, making it easier than ever to connect popular developer tools to Augment Code.

Easy MCP is a new feature in the Augment Code extension that transforms complex MCP server setup into a single click. Instead of manually configuring servers, hunting for GitHub repos, or editing JSON files, you can now connect popular developer tools with just an API token or OAuth approval.

### Available Easy MCP Integrations

Easy MCP provides one-click access to these popular developer tools:

#### CircleCI

* **Context:** Build logs, test insights, flaky-test detection
* **Sample prompt:** "Find the latest failed pipeline on my branch and surface the failing tests."
* **Setup:** Click "+", paste your CircleCI API token, and you're connected.

#### MongoDB

* **Context:** Data exploration, database management, and context-aware code generation
* **Sample prompt:** "Analyze my user collection schema and suggest optimizations for our new search feature."
* **Setup:** One-click OAuth connection to your MongoDB instance.

#### Redis

* **Context:** Keyspace introspection, TTL audits, and migration helpers
* **Sample prompt:** "Generate a migration script to move expiring session keys to the new namespace."
* **Setup:** Connect with your Redis credentials in seconds.

### Getting Started with Easy MCP

1. Open the Augment Code extension in your JetBrains IDE
2. Navigate to the Easy MCP pane in the settings
3. Click the "+" button next to your desired integration
4. Paste an API token or approve OAuth
5. Start using the integration immediately in your Agent conversations

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?maxW=1078&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d20c93ee2bfbb98f42f65f50960d2d83" className="rounded-xl" width="1078" height="646" data-path="images/EasyMCP.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=280&maxW=1078&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7562743bcfafe3cdf1270c7bfdb03ecb 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=560&maxW=1078&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=cf6a66251199e20396dcb617dc918ffa 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=840&maxW=1078&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0b80e0f064c728f0c5d70e6e87a6462a 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=1100&maxW=1078&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2eddef02672efaead7f5f2560134ef39 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=1650&maxW=1078&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8dcd0529e44cd75b6dee9b81ad5c1b1b 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=2500&maxW=1078&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f26216f491b26e758b123529de6d99c6 2500w" data-optimize="true" data-opv="2" />

From that moment on, Augment Code streams your tool's live context into every suggestion and autonomous Agent run.

## Advanced Configuration: Settings Panel

For developers who need custom MCP server configurations or want to use servers not available through Easy MCP, you can configure MCP servers manually using the Augment Settings Panel.

To access the settings panel, select the gear icon in the upper right of the Augment panel. Once the settings panel is open, you will see a section for MCP servers.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?maxW=1296&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c030e2d355bb69ddadd5d77487e23ff5" className="rounded-xl" width="1296" height="556" data-path="images/settings-panel-mcp.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=280&maxW=1296&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=5f324d22caa6e2c455100408e48e14e6 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=560&maxW=1296&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=39707fd352426506f74582e19d8643b4 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=840&maxW=1296&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=793cb5d6feffd997803b9b0d28542294 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=1100&maxW=1296&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=8cdabaee3b20f7deab04cd3a4141b178 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=1650&maxW=1296&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=7b184faea77669ff5a323fd335376b85 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=2500&maxW=1296&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=de1f03e3122d2c35786684a9a62c3a1a 2500w" data-optimize="true" data-opv="2" />

Fill in the `name` and `command` fields. The `name` field must be a unique name for the server. The `command` field is the command to run the server. Environment variables have their own section and no longer need to be specified in the command.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?maxW=1090&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0bac1e06b4b2801d73880e910f388f76" className="rounded-xl" width="1090" height="586" data-path="images/mcp-env.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=280&maxW=1090&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f9874648b300ab8ce8c77bfcd8e257ce 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=560&maxW=1090&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2d7b72d493e957c75326583fb3752e0a 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=840&maxW=1090&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=543c79cc13e1451ae80e36c4237bb1b2 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=1100&maxW=1090&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2e80ea60efe4222301b41f6c08803996 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=1650&maxW=1090&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0ea635f4c662335a67d157f064fa9005 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=2500&maxW=1090&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=bd022aa5a6fc284678b92732f417882f 2500w" data-optimize="true" data-opv="2" />

To add additional servers, click the `+` button next to the `MCP` header.
To edit a configuration or to delete a server, click the `...` button next to the server name.

### Add a Remote MCP server

If your MCP server runs remotely (for example, a hosted service), click the "+ Add remote MCP" button in the MCP section. Remote MCP connections support both HTTP and SSE (Server‑Sent Events).

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?maxW=1036&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=6dca3e0a347536258c3e6c86ebccf9c0" className="rounded-xl" width="1036" height="676" data-path="images/settings-panel-mcp-remote.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=280&maxW=1036&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=6bb4dbfdc829951d15c097159c770f6d 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=560&maxW=1036&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c78803d31505c9ef13ac44d80453cdd1 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=840&maxW=1036&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4f67ec2916fb0c6a1458f9d687de3b62 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=1100&maxW=1036&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=2d2bffa0f93629984acff533091e6eb6 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=1650&maxW=1036&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=fb7a22e8c8f9ba253ad20c36f3fa86a4 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=2500&maxW=1036&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4affc5fda8baa11a8a5edf9f57be5925 2500w" data-optimize="true" data-opv="2" />

* Connection Type: choose HTTP or SSE
* Name: a unique display name for the server
* URL: the base URL to your MCP server (e.g., [https://api.example.com](https://api.example.com))

Remote MCP servers appear alongside your local MCP servers in the list. You can edit or remove them using the "..." menu next to the server name.

## Server compatibility

Not all MCP servers are compatible with Augment's models. The MCP standard, implementation of specific servers, and Augment's MCP support are frequently being updated, so check compatibility frequently.


# Index your workspace
Source: https://docs.augmentcode.com/jetbrains/setup-augment/workspace-indexing

When your workspace is indexed, Augment can provide tailored code suggestions and answers based on your unique codebase, best practices, coding patterns, and preferences. You can always control what files are indexed.

## About indexing your workspace

When you open a workspace with Augment enabled, your codebase will be automatically uploaded to Augment's secure cloud. You can control what files get indexed using `.gitignore` and `.augmentignore` files. Indexing usually takes less than a minute but can take longer depending on the size of your codebase.

## Security and privacy

Augment stores your code securely and privately to enable our powerful context engine. We ensure code privacy through a proof-of-possession API and maintain strict internal data minimization principles. [Read more about our security](https://www.augmentcode.com/security).

## What gets indexed

Augment will index all the files in your workspace, except for the files that match patterns in your `.gitignore` file and the `.augmentignore` file.

## Ignoring files with .augmentignore

The `.augmentignore` file is a list of file patterns that Augment will ignore when indexing your workspace. Create an `.augmentignore` file in the root of your workspace. You can use any glob pattern that is supported by the [gitignore](https://git-scm.com/docs/gitignore) file.

## Including files that are .gitignored

If you have a file or directory in your `.gitignore` that you want to indexed, you can add it to your `.augmentignore` file using the `!` prefix.

For example, you may want your `node_modules` indexed to provide Augment with context about the dependencies in their project, but it is typically included in their `.gitignore`. Add `!node_modules` to your `.augmentignore` file.

<CodeGroup>
  ```bash .augmentignore
  # Include .gitignore excluded files with ! prefix
  !node_modules

  # Exclude other files with .gitignore syntax
  data/test.json
  ```

  ```bash .gitignore
  # Exclude dependencies
  node_modules

  # Exclude secrets
  .env

  # Exclude build artifacts
  out
  build
  ```
</CodeGroup>


# Using Agent
Source: https://docs.augmentcode.com/jetbrains/using-augment/agent

Use Agent to complete simple and complex tasks across your workflow–implementing a feature, upgrade a dependency, or writing a pull request.

export const type_0 = "changes"

export const AtIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M480.39-96q-79.52 0-149.45-30Q261-156 208.5-208.5T126-330.96q-30-69.96-30-149.5t30-149.04q30-69.5 82.5-122T330.96-834q69.96-30 149.5-30t149.04 30q69.5 30 122 82.5t82.5 122Q864-560 864-480v60q0 54.85-38.5 93.42Q787-288 732-288q-34 0-62.5-17t-48.66-45Q593-321 556.5-304.5T480-288q-79.68 0-135.84-56.23-56.16-56.22-56.16-136Q288-560 344.23-616q56.22-56 136-56Q560-672 616-615.84q56 56.16 56 135.84v60q0 25.16 17.5 42.58Q707-360 732-360t42.5-17.42Q792-394.84 792-420v-60q0-130-91-221t-221-91q-130 0-221 91t-91 221q0 130 91 221t221 91h192v72H480.39ZM480-360q50 0 85-35t35-85q0-50-35-85t-85-35q-50 0-85 35t-35 85q0 50 35 85t85 35Z" />
    </svg>
  </div>;

## About Agent

Augment Agent is a powerful tool that can help you complete software development tasks end-to-end. From quick edits to complete feature implementation, Agent breaks down your requests into a functional plan and implements each step all while keeping you informed about what actions and changes are happening. Powered by Augment's Context Engine and powerful LLM architecture, Agent can write, document, and test like an experienced member of your team.

## Accessing Agent

To access Agent, simply open the Augment panel and select one of the Agent modes from the drop down in the input box.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector-jetbrains.png?maxW=1265&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=85144419f1bb7b75fe28917353c752ef" alt="Augment Agent" className="rounded-xl" width="1265" height="351" data-path="images/agent-selector-jetbrains.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector-jetbrains.png?w=280&maxW=1265&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d2ebf6399ba7b67a6241c1bd92cc4ab7 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector-jetbrains.png?w=560&maxW=1265&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1d21a3200c296ced3c06c236a2f3e598 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector-jetbrains.png?w=840&maxW=1265&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=013a6607c383b5876d7629acf5efa448 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector-jetbrains.png?w=1100&maxW=1265&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3765f38c80e411be984e23a88a233aea 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector-jetbrains.png?w=1650&maxW=1265&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d87c2e7a3975dc949662242a0a341c94 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector-jetbrains.png?w=2500&maxW=1265&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2011f03fa871db3154a917cd2189e06a 2500w" data-optimize="true" data-opv="2" />

### Choosing a model

Use the model dropdown in the Augment panel to switch between Claude Sonnet 4 and GPT-5. Your selection applies only to Agent for the current workspace and can be changed at any time. See [Available Models](/models/available-models) for details.

## Using Agent

To use Agent, simply type your request into the input box using natural language and click the submit button. You will see the default context including current workspace, current file, and Agent memories. You can add additional context by clicking <AtIcon />and selecting files or folder, or add an image as context by clicking the paperclip. Agent can create, edit, or delete code across your workspace and can use tools like the terminal and external integrations through MCP to complete your request.

### Enhancing your prompt

You can improve the quality of your {type_0} by starting with a well crafted prompt. You can start with a quick or incomplete prompt and use the prompt enhancer to add relevant references, structure, and conventions from your codebase to improve the prompt before it is sent.

1. Write your prompt in the prompt input box
2. Click the Enhance Prompt ✨ button
3. Review and edit the enhanced prompt
4. Submit your prompt

### Reviewing changes

You can review every change Agent makes by clicking on the action to expand the view. Review diffs for file changes, see complete terminal commands and output, and the results of external integration calls.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-expand-jetbrains.png?maxW=1190&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7dd7ec6b0ffc1bd2997ea6c5083d4b68" alt="Augment Agent" className="rounded-xl" width="1190" height="509" data-path="images/agent-expand-jetbrains.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-expand-jetbrains.png?w=280&maxW=1190&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6f0641e5b9f47c3e9008922038d4f5f2 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-expand-jetbrains.png?w=560&maxW=1190&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7b1b4621b83beedec1f54b404c878c33 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-expand-jetbrains.png?w=840&maxW=1190&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=bbcc91b29f85aea3d1f285eab0720cb9 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-expand-jetbrains.png?w=1100&maxW=1190&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3bfba58fe048ef5e2e583ac0d1d7b3f0 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-expand-jetbrains.png?w=1650&maxW=1190&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e620906436c5b4d9a6d1dd4b8a027e45 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-expand-jetbrains.png?w=2500&maxW=1190&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6759ffa4ae79da2f56ef8254885c1ee6 2500w" data-optimize="true" data-opv="2" />

### Checkpoints

Checkpoints are automatically saved snapshots of your workspace as Agent implements the plan allowing you to easily revert back to a previous step. This enables Agent to continue working while you review code changes and commands results. To revert to a previous checkpoint, click the reverse arrow to restore your code.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint-jetbrains.png?maxW=1215&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=eae0b13183e2f7ab2f99a421d27f5a07" alt="Augment Agent" className="rounded-xl" width="1215" height="469" data-path="images/agent-checkpoint-jetbrains.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint-jetbrains.png?w=280&maxW=1215&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d693ad273a88a189b892a28229b54af5 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint-jetbrains.png?w=560&maxW=1215&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ae01dd9cd52b9081624901dc2d83c9ed 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint-jetbrains.png?w=840&maxW=1215&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b9ae49e968b5376ff54305eb34b10fd3 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint-jetbrains.png?w=1100&maxW=1215&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1fd455a762cfacff0e085a153a9eda0d 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint-jetbrains.png?w=1650&maxW=1215&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=454024abb86d0c800c0062fcf738fc25 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint-jetbrains.png?w=2500&maxW=1215&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3ab2862c7a85766646f3c51e861b591e 2500w" data-optimize="true" data-opv="2" />

### Agent vs Agent Auto

By default, Agent will pause work when it needs to execute a terminal command or access external integrations. After reviewing the suggested action, click the blue play button to have Agent execute the command and continue working. You tell Agent to skip a specific action by clicking on the three dots and then Skip.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1b04d9b700359cbd93a793a05bfee16b" alt="Augment Agent" className="rounded-xl" width="1212" height="373" data-path="images/agent-approval.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=280&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=211526cd1fe7cf7dcf5cfb52c89f2b60 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=560&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b246ebb0bf5adb7fa8edd1b5ff97302b 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=840&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a9d430ebf10aed36b2509a24f9102424 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=1100&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=662e2e65e9a3aac77ca8fa84119e8991 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=1650&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=57216409281129a06b8195f0ab4a5098 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=2500&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b0a9fb0adb44ea4d1966cdfa9cf01d75 2500w" data-optimize="true" data-opv="2" />

In Agent Auto, Agent will act more independently. It will edit files, execute terminal commands, and access tools like MCP servers automatically.

### Stop or guide the Agent

You can interrupt the Agent at any time by clicking Stop. This will pause the action to allow you to correct something you see the agent doing incorrectly. While Agent is working, you can also prompt the Agent to try a different approach which will automatically stop the agent and prompt it to correct its course.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8adf60259160c542d805bcd6dfbd71d7" alt="Stopping the agent" className="rounded-xl" width="1235" height="551" data-path="images/agent-stop.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=280&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9d29956804de18551c3b9cae1543fd00 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=560&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=13018a76b55cb0771d9eef71acf4f0a3 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=840&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f252fd53effffea19cda1bd38fe03dfa 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=1100&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=06e3604c8289c4bf9c4a305452258cbd 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=1650&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1fcb7b60297659b355ffe773204728fd 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=2500&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=14d6439fe81383ee2a908944923082a4 2500w" data-optimize="true" data-opv="2" />

### Quick Ask Mode

Quick Ask Mode is a toggle button in the agent chat interface that restricts the AI to read-only tools only. When activated, it adds a visual badge to the message and focuses the AI on information gathering without making any changes to your codebase.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=532f998cb0492e3645a9da69d758222a" alt="Quick Ask Mode toggle and usage" className="rounded-xl" width="800" height="450" data-path="images/ask-mode.gif" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=280&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0f926dcab335ce982ad465adbd847b68 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=560&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e09601fed4a527a3f6f22bd47ed52593 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=840&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a50f1f942f70e6ead193515fa2537ae7 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=1100&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3cbc23ea085ccf08f42c91bd8b41473a 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=1650&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b1f8d6f164d2244871f933f4c40f0c3a 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=2500&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=64749cbed3fc09bb51b82fbc99d02bff 2500w" data-optimize="true" data-opv="2" />

### Comparison to Chat

Agent takes Chat to the next level by allowing Augment to do things for you-that is create and make modifications directly to your codebase. Chat can explain code, create plans, and suggest changes which you can smartly apply one-by-one, but Agent takes it a step further by automatically implementing the entire plan and all code changes for you.

| What are you trying to do?                       | Chat | Agent |
| :----------------------------------------------- | :--: | :---: |
| Ask questions about your code                    |  ☑️  |   ✅   |
| Get advice on how to refactor code               |  ☑️  |   ✅   |
| Add new features to selected lines of code       |  ☑️  |   ✅   |
| Add new feature spanning multiple files          |      |   ✅   |
| Document new features                            |      |   ✅   |
| Queue up tests for you in the terminal           |      |   ✅   |
| Open Linear tickets or start a pull request      |      |   ✅   |
| Start a new branch in GitHub from recent commits |      |   ✅   |
| Automatically perform tasks on your behalf       |      |   ✅   |

### Use cases

Use Agent to handle various aspects of your software development workflow, from simple configuration changes to complex feature implementations. Agent supports your daily engineering tasks like:

* **Make quick edits** - Create a pull request to adjust configuration values like feature flags from FALSE to TRUE
* **Perform refactoring** - Move functions between files while maintaining coding conventions and ensuring bug-free operation
* **Start a first draft for new features** - Start a pull request (PR) with implementing entirely new functionality straight from a GitHub Issue or Linear Ticket
* **Branch from GitHub** - Open a PR from GitHub based on recent commits that creates a new branch
* **Query Supabase tables directly** - Ask Agent to view the contents of a table
* **Start tickets in Linear or Jira** - Open tickets and ask Agent to suggest a plan to address the ticket
* **Add Pull Request descriptions** - Merge your PR into a branch then tell the agent to explain what the changes are and why they were made
* **Create test coverage** - Generate unit tests for your newly developed features
* **Generate documentation** - Produce comprehensive documentation for your libraries and features
* **Start a README** - Write a README for a new feature or updated function that you just wrote
* **Track development progress** - Review and summarize your recent Git commits for better visibility with the GitHub integration

## Next steps

* [Configure Agent Integrations](/jetbrains/setup-augment/agent-integrations)


# Using Chat
Source: https://docs.augmentcode.com/jetbrains/using-augment/chat

Use Chat to explore your codebase, quickly get up to speed on unfamiliar code, and get help working through a technical problem.

export const type_0 = "chats"

export const DeleteIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M280-120q-33 0-56.5-23.5T200-200v-520h-40v-80h200v-40h240v40h200v80h-40v520q0 33-23.5 56.5T680-120H280Zm400-600H280v520h400v-520ZM360-280h80v-360h-80v360Zm160 0h80v-360h-80v360ZM280-720v520-520Z" />
    </svg>
  </div>;

export const ChevronRightIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M504-480 320-664l56-56 240 240-240 240-56-56 184-184Z" />
    </svg>
  </div>;

export const NewChatIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M120-160v-600q0-33 23.5-56.5T200-840h480q33 0 56.5 23.5T760-760v203q-10-2-20-2.5t-20-.5q-10 0-20 .5t-20 2.5v-203H200v400h283q-2 10-2.5 20t-.5 20q0 10 .5 20t2.5 20H240L120-160Zm160-440h320v-80H280v80Zm0 160h200v-80H280v80Zm400 280v-120H560v-80h120v-120h80v120h120v80H760v120h-80ZM200-360v-400 400Z" />
    </svg>
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About Chat

Chat is a new way to work with your codebase using natural language. Chat will automatically use the current workspace as context and you can [provide focus](/using-augment/chat-context) for Augment by selecting specific code blocks, files, folders, or external documentation. Details from your current chat, including the additional context, are used to provide more relevant code suggestions as well.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9879d970e519862e4ab098bbce847bd8" alt="Augment Chat" className="rounded-xl" width="1120" height="1209" data-path="images/chat-explain.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=280&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d0ba44e92fe571fd6cfeb40bd6dad254 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=560&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=491571511ea5171f894d977a83e03f8d 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=840&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=bdae0be74d6fd0037486829dad5b898f 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=1100&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8bd9d2dd93ecb67abbc1b74684a86561 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=1650&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=141c7d3a71afd54cc2e3ca910e5a1d6d 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=2500&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=82d357d200d56405236a3c353095847c 2500w" data-optimize="true" data-opv="2" />

## Accessing Chat

Access the Chat sidebar by clicking the Augment icon <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4eb384ca1634865b22f3c425c0e6027a" className="inline h-4 p-0 m-0" width="676" height="592" data-path="images/augment-icon-chat.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=280&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d683c31717e6be4da8863bde3cf419da 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=560&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5b89065b94498b88f97aadedb61dcaad 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=840&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=81448b7ddd95b2212098280d7129474d 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=1100&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3733a3a239dadbbb94c6600613e1a2e3 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=1650&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e9e7d6e2faecca5aabadd73d008d9a85 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=2500&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=72f66dab3541e6e71e3141a52c755331 2500w" data-optimize="true" data-opv="2" /> in the sidebar or the status bar. You can also open Chat by using one of the keyboard shortcuts below.

**Keyboard Shortcuts**

| Platform      | Shortcut                       |
| :------------ | :----------------------------- |
| MacOS         | <Keyboard shortcut="Cmd L" />  |
| Windows/Linux | <Keyboard shortcut="Ctrl L" /> |

## Using Chat

To use Chat, simply type your question or command into the input field at the bottom of the Chat panel. You will see the currently included context which includes the workspace and current file by default. Use Chat to explain your code, investigate a bug, or use a new library. See [Example Prompts for Chat](/using-augment/chat-prompts) for more ideas on using Chat.

### Enhancing your prompt

You can improve the quality of your {type_0} by starting with a well crafted prompt. You can start with a quick or incomplete prompt and use the prompt enhancer to add relevant references, structure, and conventions from your codebase to improve the prompt before it is sent.

1. Write your prompt in the prompt input box
2. Click the Enhance Prompt ✨ button
3. Review and edit the enhanced prompt
4. Submit your prompt

### Conversations about code

To get the best possible results, you can go beyond asking simple questions or commands, and instead have a back and forth conversation with Chat about your code. For example, you can ask Chat to explain a specific function and then ask follow-up questions about possible refactoring options. Chat can act as a pair programmer, helping you work through a technical problem or understand unfamiliar code.

### Starting a new chat

You should start a new Chat when you want to change the topic of the conversation since the current conversation is used as part of the context for your next question. To start a new chat, open the Augment panel and click the new chat icon <NewChatIcon /> at the top-right of the Chat panel.

### Previous chats

You can continue a chat by clicking the chevron icon<ChevronRightIcon />at the top-left of the Chat panel. Your previous chats will be listed in reverse chronological order, and you can continue your conversation where you left off.

### Deleting a chat

You can delete a previous chat by clicking the chevron icon<ChevronRightIcon />at the top-left of the Chat panel to show the list of previous chats. Click the delete icon <DeleteIcon /> next to the chat you want to delete. You will be asked to confirm that you want to delete the chat.


# Using Actions in Chat
Source: https://docs.augmentcode.com/jetbrains/using-augment/chat-actions

Actions let you take common actions on code blocks without leaving Chat. Explain, improve, or find everything you need to know about your codebase.

export const ArrowUpIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M444-192v-438L243-429l-51-51 288-288 288 288-51 51-201-201v438h-72Z" />
    </svg>
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ee847c45ac860ebd63010152269cf1fa" alt="Augment Chat Actions" className="rounded-xl" width="1233" height="630" data-path="images/chat-actions.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=280&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=11a0ee3cd4160ea86ad2e874cee1ae30 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=560&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5309c23856e22b1127b81890fdcafe23 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=840&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e8c790ce5d9b150637667dcaa640a2a9 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=1100&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=038ef29bb227d0446e760179fd21bc13 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=1650&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ee76b9ecd69421411e98e013bce0efa5 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=2500&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=26f30c2a55be51fde45b2fd8a1573c23 2500w" data-optimize="true" data-opv="2" />

## Using actions in Chat

To use a quick action, you an use a <Keyboard shortcut="/" /> command or click the up arrow icon<ArrowUpIcon />to show the available actions. For explain, fix, and test actions, first highlight the code in the editor and then use the command.

| Action                           | Usage                                                                    |
| :------------------------------- | :----------------------------------------------------------------------- |
| <Keyboard shortcut="/find" />    | Use natural language to find code or functionality                       |
| <Keyboard shortcut="/explain" /> | Augment will explain the hightlighted code                               |
| <Keyboard shortcut="/fix" />     | Augment will suggest improvements or find errors in the highlighted code |
| <Keyboard shortcut="/test" />    | Augment will suggest tests for the highlighted code                      |

Augment will typically include code blocks in the response to the action. See [Applying code blocks from Chat](/using-augment/chat-apply) for more details.


# Applying code blocks from Chat
Source: https://docs.augmentcode.com/jetbrains/using-augment/chat-apply

Use Chat to explore your codebase, quickly get up to speed on unfamiliar code, and get help working through a technical problem.

export const Availability = ({tags}) => {
  const tagTypes = {
    invite: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    beta: {
      styles: "border border-zinc-500/20 bg-zinc-50/50 dark:border-zinc-500/30 dark:bg-zinc-500/10 text-zinc-900 dark:text-zinc-200"
    },
    vscode: {
      styles: "border border-sky-500/20 bg-sky-50/50 dark:border-sky-500/30 dark:bg-sky-500/10 text-sky-900 dark:text-sky-200"
    },
    jetbrains: {
      styles: "border border-amber-500/20 bg-amber-50/50 dark:border-amber-500/30 dark:bg-amber-500/10 text-amber-900 dark:text-amber-200"
    },
    vim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    neovim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    default: {
      styles: "bg-gray-200"
    }
  };
  return <div className="flex items-center space-x-2 border-b pb-4 border-gray-200 dark:border-white/10">
      <span className="text-sm font-medium">Availability</span>
      {tags.map(tag => {
    const tagType = tagTypes[tag] || tagTypes.default;
    return <div key={tag} className={`px-2 py-0.5 rounded-md text-xs font-medium ${tagType.styles}`}>
            {tag}
          </div>;
  })}
    </div>;
};

export const MoreVertIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M479.79-192Q450-192 429-213.21t-21-51Q408-294 429.21-315t51-21Q510-336 531-314.79t21 51Q552-234 530.79-213t-51 21Zm0-216Q450-408 429-429.21t-21-51Q408-510 429.21-531t51-21Q510-552 531-530.79t21 51Q552-450 530.79-429t-51 21Zm0-216Q450-624 429-645.21t-21-51Q408-726 429.21-747t51-21Q510-768 531-746.79t21 51Q552-666 530.79-645t-51 21Z" />
    </svg>
  </div>;

export const CheckIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M389-267 195-460l51-52 143 143 325-324 51 51-376 375Z" />
    </svg>
  </div>;

export const FileNewIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M200-120q-33 0-56.5-23.5T120-200v-560q0-33 23.5-56.5T200-840h360v80H200v560h560v-360h80v360q0 33-23.5 56.5T760-120H200Zm120-160v-80h320v80H320Zm0-120v-80h320v80H320Zm0-120v-80h320v80H320Zm360-80v-80h-80v-80h80v-80h80v80h80v80h-80v80h-80Z" />
    </svg>
  </div>;

export const FileCopyIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M760-200H320q-33 0-56.5-23.5T240-280v-560q0-33 23.5-56.5T320-920h280l240 240v400q0 33-23.5 
      56.5T760-200ZM560-640v-200H320v560h440v-360H560ZM160-40q-33 0-56.5-23.5T80-120v-560h80v560h440v80H
      160Zm160-800v200-200 560-560Z" />
    </svg>
  </div>;

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=774a796e289508034253da0a4eadda1d" alt="Augment Chat Apply" className="rounded-xl" width="1291" height="375" data-path="images/chat-apply.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=280&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=683274bfa6a97c689d21fa510b8c924a 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=560&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=411bc80d62b14c9ebdafd16f6bdf1816 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=840&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e3dc1ed2eb6bfe30bb082b19694f5054 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=1100&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6a996e95e03a2d613efa21fa2d18531f 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=1650&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f8bcfcfcef62342687b25edcf5ede82d 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=2500&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ab7acba48cc20358a9910b46f4c9ce24 2500w" data-optimize="true" data-opv="2" />

## Using code blocks from within Chat

Whenever Chat responds with code, you will have the option to add the code to your codebase. The most common option will be shown as a button and you can access the other options by clicking the overflow menu icon<MoreVertIcon />at the top-right of the code block. You can use the following options to apply the code:

* <FileCopyIcon />**Copy**
  the code from the block to your clipboard
* <FileNewIcon />**Create**
  a new file with the code from the block
* <CheckIcon />**Apply**
  the code from the block intelligently to your file


# Focusing Context in Chat
Source: https://docs.augmentcode.com/jetbrains/using-augment/chat-context

You can specify context from files, folders, and external documentation in your conversation to focus your chat responses.

export const AtIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M480.39-96q-79.52 0-149.45-30Q261-156 208.5-208.5T126-330.96q-30-69.96-30-149.5t30-149.04q30-69.5 82.5-122T330.96-834q69.96-30 149.5-30t149.04 30q69.5 30 122 82.5t82.5 122Q864-560 864-480v60q0 54.85-38.5 93.42Q787-288 732-288q-34 0-62.5-17t-48.66-45Q593-321 556.5-304.5T480-288q-79.68 0-135.84-56.23-56.16-56.22-56.16-136Q288-560 344.23-616q56.22-56 136-56Q560-672 616-615.84q56 56.16 56 135.84v60q0 25.16 17.5 42.58Q707-360 732-360t42.5-17.42Q792-394.84 792-420v-60q0-130-91-221t-221-91q-130 0-221 91t-91 221q0 130 91 221t221 91h192v72H480.39ZM480-360q50 0 85-35t35-85q0-50-35-85t-85-35q-50 0-85 35t-35 85q0 50 35 85t85 35Z" />
    </svg>
  </div>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About Chat Context

Augment intelligently includes context from your entire workspace based on the ongoing conversation–even if you don't have the relevant files open in your editor–but sometimes you want Augment to prioritize specific details for more relevant responses.

<video src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-context.mp4?auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8209f4f16256b74970f18e1aec456f8e" loop muted controls className="rounded-xl" data-path="images/chat-context.mp4" />

### Focusing context for your conversation

You can specify context by clicking the <AtIcon /> icon at the top-left of the Chat panel or by <Command text="@-mentioning" /> in the input field. You can use fuzzy search to filter the list of context options quickly. There are a number of different types of additional context you can add to your conversation:

1. Highlighted code blocks
2. Specific files or folders within your workspace
3. 3rd party documentation, like Next.js documentation

#### Mentioning files and folders

Include specific files or folders in your context by typing `@` followed by the file or folder name. For example, `@routes.tsx` will include the `routes.tsx` file in your context. You can include multiple files or folders.

#### Mentioning 3rd party documentation

You can also mention 3rd party documentation in your context by typing `@` followed by the name of the documentation. For example, `@Next.js` will include Next.js documentation in your context. Augment provides nearly 300 documentation sets spanning across a wide range of domains such as programming languages, packages, software tools, and frameworks.


# Example Prompts for Chat
Source: https://docs.augmentcode.com/jetbrains/using-augment/chat-prompts

Using natural language to interact with your codebase unlocks a whole new way of working. Learn how to get the most out of Chat with the following example prompts.

export const type_0 = "chats"

## About chatting with your codebase

Augment's Chat has deep understanding about your codebase, dependencies, and best practices. You can use Chat to ask questions about your code, but it also can help you with general software engineering questions, think through technical decisions, explore new libraries, and more.

## Enhancing your prompt

You can improve the quality of your {type_0} by starting with a well crafted prompt. You can start with a quick or incomplete prompt and use the prompt enhancer to add relevant references, structure, and conventions from your codebase to improve the prompt before it is sent.

1. Write your prompt in the prompt input box
2. Click the Enhance Prompt ✨ button
3. Review and edit the enhanced prompt
4. Submit your prompt

## Example Prompts

### Explain code

* Explain this codebase to me
* How do I use the Twilio API to send a text message?
* Explain how generics work in TypeScript and give me a simple example

### Finding code

* Where are all the useEffect hooks that depend on the 'currentUser' variable?
* Find the decorators that implement retry logic across our microservices
* Find coroutines that handle database transactions without a timeout parameter

### Generate code

* Write a function to check if a string is a valid email address
* Generate a middleware function that rate-limits API requests using a sliding window algorithm
* Create a SQL query to find the top 5 customers who spent the most money last month

### Write tests

* Write integration tests for this API endpoint
* What edge cases have I not included in this test?
* Generate mock data for testing this customer order processing function

### Refactor and improve code

* This function is running slowly with large collections - how can I optimize it?
* Refactor this callback-based code to use async/await instead
* Rewrite this function in Rust

### Find and fix errors

* This endpoint sometimes returns a 500 error. Here's the error log - what's wrong?
* I'm getting 'TypeError: Cannot read property 'length' of undefined' in this component.
* Getting CORS errors when my frontend tries to fetch from the API


# Completions
Source: https://docs.augmentcode.com/jetbrains/using-augment/completions

Use code completions to get more done. Augment's radical context awareness means more relevant suggestions, fewer hallucinations, and less time hunting down documentation.

export const MoreVertIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M479.79-192Q450-192 429-213.21t-21-51Q408-294 429.21-315t51-21Q510-336 531-314.79t21 51Q552-234 530.79-213t-51 21Zm0-216Q450-408 429-429.21t-21-51Q408-510 429.21-531t51-21Q510-552 531-530.79t21 51Q552-450 530.79-429t-51 21Zm0-216Q450-624 429-645.21t-21-51Q408-726 429.21-747t51-21Q510-768 531-746.79t21 51Q552-666 530.79-645t-51 21Z" />
    </svg>
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About Code Completions

Augment's Code Completions integrates with your IDE's native completions system to give you autocomplete-like suggestions as you type. You can accept all of a suggestion, accept partial suggestions a word or a line at a time, or just keep typing to ignore the suggestion.

## Using Code Completions

To use code completions, simply start typing in your IDE. Augment will provide suggestions based on the context of your code. You can accept a suggestion by pressing <Keyboard shortcut="Tab" />, or ignore it by continuing to type.

For example, add the following function to a TypeScript file:

```typescript
function getUser(): Promise<User>;
```

As you type `getUser`, Augment will suggest the function signature. Press <Keyboard shortcut="Tab" /> to accept the suggestion. Augment will continue to offer suggestions until the function is complete, at which point you will have a function similar to:

```typescript
function getUser(): Promise<User> {
  return fetch("/api/user/1")
    .then((response) => response.json())
    .then((json) => {
      return json as User;
    });
}
```

### Accepting Completions

<Tabs>
  <Tab title="MacOS">
    <Tip>
      We recommend configuring a custom keybinding to accept a word or line, see
      [Keyboard shortcuts](/setup-augment/vscode-keyboard-shortcuts) for more
      details.
    </Tip>

    | Action                         | Default keyboard shortcut                       |
    | :----------------------------- | :---------------------------------------------- |
    | Accept inline suggestion       | <Keyboard shortcut="Tab" />                     |
    | Accept next word of suggestion | <Keyboard shortcut="Cmd →" />                   |
    | Accept next line of suggestion | None (see above)                                |
    | Reject suggestion              | <Keyboard shortcut="Esc" />                     |
    | Ignore suggestion              | Continue typing through the suggestion          |
    | Toggle automatic completions   | VSCode: <Keyboard shortcut="Cmd Option A" />    |
    |                                | JetBrains: <Keyboard shortcut="Cmd Option 9" /> |
  </Tab>

  <Tab title="Windows/Linux">
    <Tip>
      We recommend configuring a custom keybinding to accept a word or line, see
      [Keyboard shortcuts](/setup-augment/vscode-keyboard-shortcuts) for more
      details.
    </Tip>

    | Action                         | Default keyboard shortcut                     |
    | :----------------------------- | :-------------------------------------------- |
    | Accept inline suggestion       | <Keyboard shortcut="Tab" />                   |
    | Accept next word of suggestion | <Keyboard shortcut="Ctrl →" />                |
    | Accept next line of suggestion | None (see above)                              |
    | Reject suggestion              | <Keyboard shortcut="Esc" />                   |
    | Ignore suggestion              | Continue typing through the suggestion        |
    | Toggle automatic completions   | VSCode: <Keyboard shortcut="Ctrl Alt A" />    |
    |                                | JetBrains: <Keyboard shortcut="Ctrl Alt 9" /> |
  </Tab>
</Tabs>

### Disabling Completions

<Tabs>
  <Tab title="Visual Studio Code">
    You can disable automatic code completions by clicking the overflow menu icon<MoreVertIcon />at the top-right of the Augment panel, then selecting <Command text="Turn Automatic Completions Off" />.
  </Tab>

  <Tab title="JetBrains IDEs">
    You can disable automatic code completions by clicking the Augment icon <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0f98e2222af9b74b38faeb8c56ed09be" className="inline h-3 p-0 m-0" width="18" height="12" data-path="images/augment-icon-smile.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=280&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a8dbbf105bd40aba81b68a8d4a201a9b 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=560&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ceadb84e919f3b37196015245795a07b 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=840&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1429216a05326906607010bb8f5b6c5f 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1100&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2baf591f8e787b1fe0d597f94d07fa9a 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1650&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2d12c3d3d9908f5059b1ad5cf5403402 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=2500&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=903c35569e24b232be24f720a097f896 2500w" data-optimize="true" data-opv="2" /> in the status bar at the bottom right corner of your IDE, then selecting <Command text="Disable Completions" />.
  </Tab>
</Tabs>

### Enable Completions

<Tabs>
  <Tab title="Visual Studio Code">
    If you've temporarily disabled completions, you can re-enable them by clicking the overflow menu icon<MoreVertIcon />at the top-right of the Augment panel, then selecting <Command text="Turn Automatic Completions On" />.
  </Tab>

  <Tab title="JetBrains IDEs">
    If you've temporarily disabled completions, you can re-enable them by clicking the Augment icon <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0f98e2222af9b74b38faeb8c56ed09be" className="inline h-3 p-0 m-0" width="18" height="12" data-path="images/augment-icon-smile.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=280&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a8dbbf105bd40aba81b68a8d4a201a9b 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=560&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ceadb84e919f3b37196015245795a07b 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=840&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1429216a05326906607010bb8f5b6c5f 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1100&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2baf591f8e787b1fe0d597f94d07fa9a 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1650&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2d12c3d3d9908f5059b1ad5cf5403402 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=2500&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=903c35569e24b232be24f720a097f896 2500w" data-optimize="true" data-opv="2" /> in the status bar at the bottom right corner of your IDE, then selecting <Command text="Enable Completions" />.
  </Tab>
</Tabs>


# Using Tasklist
Source: https://docs.augmentcode.com/jetbrains/using-augment/tasklist

Use Tasklist to break down complex problems into manageable steps, track progress, and collaborate with Agent on multi-step tasks.

## What is the Tasklist?

Augment's Tasklist helps the Agent create and refine a step-by-step plan for you to review. The Tasklist provides a structured interface for collaboration between you and the Agent, allowing you to break down complex problems into manageable, sequential steps.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=66106132e60b28a7322afc66cd3339cd" alt="Tasklist Overview" className="rounded-xl" width="473" height="208" data-path="images/tasklist-overview.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=280&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c52e38fbb502e66483849cab4cbc4f24 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=560&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=14a7face2e25e20be8da3efef5212df4 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=840&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=ef44a0f558f375f3ee90c34d34a7e775 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=1100&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=0cfd78964a6e27f197a0ee33fe53f5fd 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=1650&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d50b54f3846315cd1035cc0e74013061 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=2500&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3e46bef1c9509c706c94380320f7bbd7 2500w" data-optimize="true" data-opv="2" />

## Why Tasklist?

Tasklist improves agent effectiveness on long or complex tasks by:

* **Maintaining context** across different conversations by moving your Tasklist to a new chat
* **Breaking down complex problems** into manageable, sequential steps
* **Gathering progress** across threads
* **Exploring alternative solutions** to completed tasks if you need to pivot
* **Streamlining your approach** to nebulous problems by deleting irrelevant steps once the path forward is clear

Tasklist provides a structured interface for collaboration and opens up possibilities for agent-to-agent collaboration. We hypothesize that an interface such as Tasklist could be a preferred way to interact with coding agents in the future.

## Tasklist in Action

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-demo.gif?maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=9418f98f7cfc55c34020ac5d442d9f92" alt="Tasklist demonstration" className="rounded-xl" width="800" height="542" data-path="images/tasklist-demo.gif" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-demo.gif?w=280&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=ad6abc45c348c4bc1a1502c0398079db 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-demo.gif?w=560&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e515b0258d3fe18f1fd1136056ddd9ca 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-demo.gif?w=840&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=dc021270635d13a0b06fd8eac7bb6b56 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-demo.gif?w=1100&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c83d901d6c76c6c3c0c02b6512afc7a3 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-demo.gif?w=1650&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=5c26f13e27d825ef533308b94ae3f769 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-demo.gif?w=2500&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c0b2eec1008dad629aca1865720021cc 2500w" data-optimize="true" data-opv="2" />

## Creating a New Task

### Automatic Creation

The Agent will usually create a Tasklist when it encounters a complex, multi-step problem. You can also ask the Agent to make a Tasklist for you by simply prompting "Start a Tasklist to..." then add the problem you are trying to tackle.

### Manual Creation

You can also manually create a Tasklist:

1. Switch to Tasklist using the checklist button next to Changes
2. Click the plus to add your first task
3. Alternatively, you can create a new task by typing in the gray prompt box at the bottom of the extension. Click **Add Task** from the dropdown arrow next to Send

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e466e5fd63059be47b3fa71c4be44d0d" alt="Creating a new task" className="rounded-xl" width="473" height="85" data-path="images/tasklist-create-task.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=280&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a41aa2a6227553600523a44e07c667b7 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=560&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=84b30971faa8116b5fb6d5c13b0feeeb 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=840&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=73b351aae0779181ab8fde87c01c848e 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=1100&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=827874c7324570617e29684689c8966b 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=1650&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=5f28d1d2cd55b970b41324c65e56271d 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=2500&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b858589667a93796b5a533466d7fb5cb 2500w" data-optimize="true" data-opv="2" />

## Running Tasks

To run a task, click the grey triangle (play button) next to the task. The Agent will begin executing the task and update its status as it progresses.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?maxW=824&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=adb5c8fad4259a3cc1f760f0788d30ba" alt="Running a task" className="rounded-xl" width="824" height="778" data-path="images/tasklist-run-task.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=280&maxW=824&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a7418ca0802c4eb8d201e7474d0168f1 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=560&maxW=824&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=dfafae271c229987e07770aaf1fd624f 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=840&maxW=824&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a1f25af866cd811e02dbd4b384f596ba 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=1100&maxW=824&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=9eb9208cce811ac708bdf5be7682642f 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=1650&maxW=824&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=536f067eff5a32f927f29f07ace3e579 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=2500&maxW=824&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=918d2a234070905f2f048d83109c6d25 2500w" data-optimize="true" data-opv="2" />

## Task Status Indicators

Task statuses are indicated by different colors and icons:

* **Empty circle** - Task has not yet started
* **Blue half circle** - Task is currently in progress
* **Green checkbox** - Task has been completed and is ready for review

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4d62dc399deb414637cac1b89bf2a99f" alt="Task status indicators" className="rounded-xl" width="473" height="214" data-path="images/tasklist-status-indicators.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=280&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=9809f37b08a79dc806d693dcbd847ea0 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=560&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=f9b5d68a336d51a770abbb5eff126ec1 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=840&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e3488c9e1723834bc4b4fa8d99393407 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=1100&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4287c08828714469e5bb7f1048bd36fa 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=1650&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=8b673b67e729ba79f03abb8caf723242 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=2500&maxW=473&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e5b44fedafdfc55d297de689a196e0f4 2500w" data-optimize="true" data-opv="2" />

## Subtasks

Augment Code automatically generates subtasks when needed. The Agent will automatically add and nest required subtasks under your initial tasks. You can edit and expand these subtasks just like any other task in the list. Likewise, you can remove subtasks you deem unnecessary.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?maxW=233&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=be4ec77f305dead390a1b3e6d965a8b9" alt="Subtasks example" className="rounded-xl" width="233" height="32" data-path="images/tasklist-subtasks.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=280&maxW=233&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=caeab6d941eb0ca5a8da719a485f315c 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=560&maxW=233&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=17e7afdd150e955a8fb447f13594bc04 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=840&maxW=233&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=cfed0c41520d8d0a2a8da549587d5691 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=1100&maxW=233&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=dcc5edf6a215a325dcaaf0765f382d4a 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=1650&maxW=233&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a63529a6d99922d36e81d109c0a68c9e 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=2500&maxW=233&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=fb84a2f274c4fdb7a26f0d3ef62743bb 2500w" data-optimize="true" data-opv="2" />

## Managing Running Tasks

### Stopping a Task

You can treat any in-progress task like any prompt you might send the Agent. To stop what the Agent is doing and offer a corrective action, click the red square (stop button) and tell the Agent what you want it to do instead.

### Running All Tasks

The Agent can complete all the tasks sequentially by clicking the triangle (play button) at the top of the Tasklist.

## Reviewing Changes

You can review the changes made by the Agent after a task is completed by toggling between the Tasks and Changes view to see the diffs (differences) of the work done by the agent for each task.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?maxW=818&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c93a7c7ba692ca5cba7e2c789e889a8c" alt="Reviewing changes in Tasks and Changes view" className="rounded-xl" width="818" height="364" data-path="images/tasklist-changes-view.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=280&maxW=818&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=255ce5c4a62ea150e933dac66d3706b6 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=560&maxW=818&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=0600277a3cdd05c4393bcda9b36c8f3a 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=840&maxW=818&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a501b1afbed0c5beb70fbc2cad3e5e56 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=1100&maxW=818&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=8789fc3c72e5092a0a07b64ed3bc555b 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=1650&maxW=818&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=9e825b836b1d9134a30661558edd8e76 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=2500&maxW=818&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=45a9ee720d0949cad7ccbd102d5091e7 2500w" data-optimize="true" data-opv="2" />

## Integration with Task Management Tools

### Jira and Linear Integration

The Tasklist is a perfect pairing with existing task management tools like Jira or Linear:

* Ask the Agent to create a Tasklist based on tickets inside Jira or Linear
* Further break down complex tickets into manageable steps
* Once your Tasklist is completed, you can ask the Agent to resolve the issue inside Jira or Linear and append the steps taken as a comment

### Standalone Usage

Don't use an issue tracker? No problem - use Tasklist to track issues you need to tackle across Threads.

## Best Practices

* **Be specific** when creating tasks to help the Agent understand exactly what needs to be done
* **Review and edit** the automatically generated subtasks to ensure they align with your goals
* **Use the stop function** to provide course corrections when the Agent is heading in the wrong direction
* **Leverage the Changes view** to review all modifications made during task execution
* **Move Tasklists** between conversations to maintain context across different chat sessions

## Next Steps

* [Learn more about Agent](/jetbrains/using-augment/agent)
* [Configure Agent Integrations](/jetbrains/setup-augment/agent-integrations)


# Available Models
Source: https://docs.augmentcode.com/models/available-models

The LLMs currently available in Augment and how we use them.

## Current models

Augment uses world-class large language models together with our Context Engine. We currently support the following models:

* Claude Sonnet 4 by Anthropic
* GPT-5 by OpenAI

## Choosing a model

You can select the model directly using the Model Picker in the Augment panel. Choose between Claude Sonnet 4 and GPT-5 based on your preference or task needs.

* In VS Code and JetBrains, open the Augment panel and use the model dropdown near the input box to switch models.
* Your selection applies only to Agent in that workspace and can be changed at any time.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/model-picker.jpg?maxW=562&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=338d69b245937cdf833823eb969b1bef" alt="Model Picker in Augment panel" className="rounded-xl" width="562" height="260" data-path="images/model-picker.jpg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/model-picker.jpg?w=280&maxW=562&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3022a3efe7d6e7aac31de4f9e6a7e86c 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/model-picker.jpg?w=560&maxW=562&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ba0c9c48358244d51c9787c88bd33e56 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/model-picker.jpg?w=840&maxW=562&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7268017722f8fedebc1c00478fa16599 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/model-picker.jpg?w=1100&maxW=562&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=bf7c5dfd0135c4ff06bc76a5870c94a7 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/model-picker.jpg?w=1650&maxW=562&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=80db34f3e6d6917a10837d2179f1441c 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/model-picker.jpg?w=2500&maxW=562&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ac6c2f0844f423916a292a27ede95596 2500w" data-optimize="true" data-opv="2" />

If you don't pick a model, Augment will use your last selection or the default set by your organization.

## Feature compatibility

Both models support the core Augment Agent features:

* Deep code understanding with Augment's Context Engine
* Tool use (integrations and MCP), file edits, and multi-step planning

Some behaviors (e.g., wording or style) may vary slightly between models. We'll continue to refine prompts and guardrails to provide a consistent developer experience.

## Notes and transparency

* We may roll out model updates gradually. If you're part of a staged rollout, different workspaces or teammates may see updates at different times.
* For troubleshooting, you can share the request ID with our support team; they can confirm which model handled a specific request.

If you have questions about model availability or want to participate in early access programs, please reach out via Support.


# Quickstart
Source: https://docs.augmentcode.com/quickstart

Augment is the developer AI for teams that deeply understands your codebase and how you build software. Your code, your dependencies, and your best practices are all at your fingertips.

export const Next = ({children}) => <div className="border-t border-b pb-8 border-gray dark:border-white/10">
    <h3>Next steps</h3>
    {children}
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

### 1. Install the Augment extension

<CardGroup cols={3}>
  <Card href="https://marketplace.visualstudio.com/items?itemName=augment.vscode-augment">
    <img className="w-12 h-12" src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b6d0dafb62816d87fb9996ea8af5e25e" alt="Visual Studio Code" width="64" height="64" data-path="images/vscode-icon.svg" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=280&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=8a8f401bdacbb6a397e28030e0610e28 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=560&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3cb81100f08c3223e70740ea3e20d7dd 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=840&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=f71758a22683cdc9e08bf703b1974b08 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=1100&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=86aeb522022e61b3f70f0ebec5d586ec 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=1650&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=cfbe41cb1bdf9c79bac51c7844be89b6 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-icon.svg?w=2500&maxW=64&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=48b8399d625178d62d883889647b7d91 2500w" data-optimize="true" data-opv="2" />

    <h2 className="pt-4 font-semibold text-base text-gray-800 dark:text-white">
      Visual Studio Code
    </h2>

    <p>Install Augment for Visual Studio Code</p>
  </Card>

  <Card className="bg-red" href="https://plugins.jetbrains.com/plugin/24072-augment">
    <img className="w-12 h-12" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4cf0e1e9968e1dd6ef465d292aa5b507" alt="JetBrains IDEs" width="64" height="64" data-path="images/jetbrains-icon.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=280&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9b4f573392cdff10ac1b019b5aa576f3 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=560&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1aeb7a8a9645688cff751bf264f6d5bb 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=840&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4f4a505397fbe4100c9dbf16c0597793 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=1100&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e7f21219990815a15d018e71e58fa7eb 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=1650&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4538c670242c92afa3dc0f9b6b37e4bf 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/jetbrains-icon.svg?w=2500&maxW=64&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=562de59a3e122c81c162bb6d0dd82a1a 2500w" data-optimize="true" data-opv="2" />

    <h2 className="pt-4 font-semibold text-base text-gray-800 dark:text-white">
      JetBrains IDEs
    </h2>

    <p>Install Augment for JetBrains IDEs, including WebStorm, PyCharm, and IntelliJ</p>
  </Card>

  <Card className="bg-red" href="/vim/setup-augment/install-vim-neovim">
    <img className="w-12 h-12" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f8bcad890f46810d3554bd3902d2c810" alt="Vim and Neovim" width="24" height="24" data-path="images/neovim-logo.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=280&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e9abfadd0177662c13b6ad717515ef80 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=560&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9380e4ad3fb7293545668ab44d1ac10a 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=840&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e12d0db7ed0199e1bdb982b14acc7fe9 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=1100&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e4f30e851dd968fbeec2d469bc0ec889 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=1650&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8e728c1b6f1b98f01cc8a32a3df249c9 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/neovim-logo.svg?w=2500&maxW=24&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8dd8e9292c4ecc9ecf0ffeb5d3c202b0 2500w" data-optimize="true" data-opv="2" />

    <h2 className="pt-4 font-semibold text-base text-gray-800 dark:text-white">
      Vim and Neovim
    </h2>

    <p>
      Get completions and chat in your favorite text editor.
    </p>
  </Card>
</CardGroup>

### 2. Sign-in and sync your repository

For VS Code and JetBrains IDEs, follow the prompts in the Augment panel to [sign in](/setup-augment/sign-in) and [index your workspace](/setup-augment/workspace-indexing). If you don't see the Augment panel, press <Keyboard shortcut="Cmd/Ctrl L" /> or click the Augment icon in the side panel of your IDE.

For Vim and Neovim, use the command `:Augment signin` to sign in.

### 3. Start coding with Augment

<Steps>
  <Step title="Using chat">
    Augment Chat enables you to work with your codebase using natural language.
    Ask Chat to explain your codebase, help you get started with debugging an
    issue, or writing entire functions and tests. See [Using
    Chat](/using-augment/chat) for more details.
  </Step>

  <Step title="Using Next Edit">
    Augment Next Edit keeps you moving through your tasks by guiding you step-by-step through complex or repetitive changes. Jump to the next suggestion–in the same file or across your codebase–by pressing <Keyboard shortcut="Cmd/Ctrl ;" />. See
    [Using Next Edit](/using-augment/next-edit) for more details.
  </Step>

  <Step title="Using instructions">
    Start using an Instruction by hitting <Keyboard shortcut="Cmd/Ctrl I" /> and quickly write tests, refactor code, or craft any prompt in natural language to transform your code. See [Using
    Instructions](/using-augment/instructions) for more details.
  </Step>

  <Step title="Using completions">
    Augment provides inline code suggestions as you type. To accept the full
    suggestions, press <Keyboard shortcut="Tab" />, or accept the suggestion one
    word at a time with <Keyboard shortcut="Cmd/Ctrl →" />. See [Using
    Completions](/using-augment/completions) for more details.
  </Step>
</Steps>

<Next>
  * [Disable other code assistants](/troubleshooting/disable-copilot)
  * [Use keyboard shortcuts](/setup-augment/vscode-keyboard-shortcuts)
  * [Configure indexing](/setup-augment/workspace-indexing)
</Next>


# Agent Integrations
Source: https://docs.augmentcode.com/setup-augment/agent-integrations

Configure integrations for Augment Agent to access external services like GitHub, Linear, Jira, Confluence, Notion, Sentry, and Stripe.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const StripeLogo = () => <svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path d="M13.976 9.15c-2.172-.806-3.356-1.426-3.356-2.409 0-.831.683-1.305 1.901-1.305 2.227 0 4.515.858 6.09 1.631l.89-5.494C18.252.274 15.697 0 12.165 0 9.667 0 7.589.654 6.104 1.872 4.56 3.147 3.757 4.992 3.757 7.218c0 4.039 2.467 5.76 6.476 7.219 2.585.92 3.445 1.574 3.445 2.583 0 .98-.84 1.545-2.354 1.545-1.875 0-4.965-.921-6.99-2.109l-.9 5.555C5.175 22.99 8.385 24 11.714 24c2.641 0 4.843-.624 6.328-1.813 1.664-1.305 2.525-3.236 2.525-5.732 0-4.128-2.524-5.851-6.591-7.305z" fill="currentColor" />
  </svg>;

export const SentryLogo = () => <svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm0 18c-4.41 0-8-3.59-8-8s3.59-8 8-8 8 3.59 8 8-3.59 8-8 8z" fill="currentColor" />
    <path d="M12 6c-3.31 0-6 2.69-6 6h2c0-2.21 1.79-4 4-4s4 1.79 4 4-1.79 4-4 4v2c3.31 0 6-2.69 6-6s-2.69-6-6-6z" fill="currentColor" />
    <circle cx="12" cy="12" r="2" fill="currentColor" />
  </svg>;

export const GleanLogo = () => <svg width="24" height="24" viewBox="0 0 16 16" fill="none" xmlns="http://www.w3.org/2000/svg">
  <path fill-rule="evenodd" clip-rule="evenodd" d="M8.95113 2.67649L10.2775 1L11.887 2.24179L10.5704 3.906C11.25 4.70862 11.6591 5.74239 11.6591 6.87053C11.6591 9.42425 9.56277 11.4945 6.9768 11.4945C4.39084 11.4945 2.29451 9.42425 2.29451 6.87053C2.29451 4.31677 4.39084 2.24655 6.9768 2.24655C7.68222 2.24655 8.35119 2.4006 8.95113 2.67649ZM6.9768 9.50853C5.50146 9.50853 4.30546 8.32747 4.30546 6.87053C4.30546 5.41358 5.50146 4.23245 6.9768 4.23245C8.45215 4.23245 9.64814 5.41358 9.64814 6.87053C9.64814 8.32747 8.45215 9.50853 6.9768 9.50853ZM11.7135 10.8261C11.5975 10.9618 11.4753 11.0913 11.3477 11.2173C11.2202 11.3424 11.0873 11.4622 10.949 11.5758C10.8116 11.6894 10.6689 11.7969 10.5208 11.8982C10.3736 11.9995 10.2211 12.0955 10.065 12.1837C9.90978 12.2726 9.75012 12.3537 9.58684 12.4286C9.42448 12.5034 9.25856 12.5712 9.08906 12.6311C8.92046 12.6919 8.74919 12.7448 8.57434 12.7898C8.40217 12.8365 8.22645 12.8743 8.04892 12.9043C7.87319 12.9351 7.69478 12.958 7.51459 12.973C7.33706 12.988 7.15776 12.9959 6.97667 12.9959C6.79558 12.9959 6.61628 12.988 6.43876 12.973C6.25856 12.958 6.08016 12.9351 5.90441 12.9043C5.7269 12.8743 5.55116 12.8365 5.379 12.7898L4.85357 14.726C5.08194 14.7868 5.31565 14.838 5.55206 14.8784C5.78488 14.919 6.02217 14.9498 6.26213 14.9692C6.49763 14.9895 6.73582 15 6.97667 15C7.21753 15 7.4557 14.9895 7.69121 14.9692C7.93117 14.9498 8.16756 14.919 8.40129 14.8784C8.63768 14.838 8.87051 14.7868 9.09977 14.726C9.33171 14.6662 9.56007 14.5957 9.7831 14.5147C10.0088 14.4345 10.2291 14.3446 10.445 14.2451C10.6617 14.1455 10.8741 14.0372 11.0802 13.92C11.2871 13.802 11.4887 13.6751 11.684 13.5394C11.8803 13.4047 12.0704 13.2619 12.2532 13.1104C12.437 12.9589 12.6136 12.8003 12.7822 12.6338C12.9517 12.4673 13.1131 12.2946 13.2675 12.1141C13.4218 11.9343 13.5681 11.7467 13.7055 11.5538L12.0435 10.4041C11.9401 10.5495 11.8295 10.6905 11.7135 10.8261Z" fill="currentColor" />
</svg>;

export const ConfluenceLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M2.43703 10.7785C2.30998 10.978 2.16478 11.2137 2.05588 11.3951C1.94698 11.5764 2.00143 11.8121 2.18293 11.921L4.66948 13.4442C4.85098 13.553 5.08695 13.4986 5.19585 13.3173C5.2866 13.1541 5.41365 12.9365 5.55885 12.7007C6.53895 11.0868 7.5372 11.2681 9.3159 12.1204L11.7843 13.281C11.9839 13.3717 12.2017 13.281 12.2925 13.0997L13.4722 10.4339C13.563 10.2526 13.4722 10.0169 13.2907 9.92619C12.7644 9.69044 11.7298 9.20084 10.8223 8.74749C7.44645 7.13354 4.59689 7.24234 2.43703 10.7785Z" fill="currentColor" />
  <path d="M13.563 4.72157C13.69 4.52209 13.8352 4.28635 13.9441 4.105C14.053 3.92366 13.9985 3.68791 13.817 3.57911L11.3305 2.05583C11.149 1.94702 10.913 2.00143 10.8041 2.18277C10.7134 2.34598 10.5863 2.56359 10.4411 2.79934C9.461 4.41329 8.46275 4.23194 6.68405 3.37963L4.21563 2.21904C4.01598 2.12837 3.79818 2.21904 3.70743 2.40038L2.52767 5.0661C2.43692 5.24745 2.52767 5.4832 2.70917 5.5739C3.23552 5.80965 4.27007 6.29925 5.1776 6.7526C8.53535 8.34845 11.3849 8.25775 13.563 4.72157Z" fill="currentColor" />
</svg>;

export const JiraLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg"><path fill-rule="evenodd" clip-rule="evenodd" d="M13.5028 2H7.7257C7.7257 3.44 8.8914 4.60571 10.3314 4.60571H11.3942V5.6343C11.3942 7.0743 12.5599 8.24 14 8.24V2.49714C14 2.22285 13.7771 2 13.5028 2ZM10.6399 4.88H4.86279C4.86279 6.32 6.0285 7.4857 7.4685 7.4857H8.53135V8.5143C8.53135 9.9543 9.69705 11.12 11.137 11.12V5.37715C11.137 5.10285 10.9142 4.88 10.6399 4.88ZM2 7.75995H7.7771C8.0514 7.75995 8.27425 7.9828 8.27425 8.2571V13.9999C6.83425 13.9999 5.66855 12.8342 5.66855 11.3942V10.3656H4.6057C3.16571 10.3656 2 9.19995 2 7.75995Z" fill="currentColor" />
</svg>;

export const NotionLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path d="M3.47498 3.32462C3.92288 3.68848 4.0909 3.66071 4.93192 3.60461L12.8609 3.12851C13.029 3.12851 12.8892 2.96075 12.8332 2.93286L11.5163 1.98091C11.264 1.78502 10.9278 1.56068 10.2835 1.6168L2.60594 2.17678C2.32595 2.20454 2.27001 2.34453 2.38153 2.45676L3.47498 3.32462ZM3.95103 5.17244V13.5151C3.95103 13.9634 4.17508 14.1312 4.67938 14.1035L13.3933 13.5992C13.8978 13.5715 13.954 13.263 13.954 12.8989V4.61222C13.954 4.24858 13.8142 4.05248 13.5053 4.08047L4.39915 4.61222C4.06311 4.64046 3.95103 4.80855 3.95103 5.17244ZM12.5534 5.61996C12.6093 5.87218 12.5534 6.12417 12.3007 6.15251L11.8808 6.23616V12.3952C11.5163 12.5911 11.1801 12.7031 10.9 12.7031C10.4516 12.7031 10.3392 12.5631 10.0033 12.1433L7.257 7.83198V12.0034L8.12602 12.1995C8.12602 12.1995 8.12602 12.7031 7.4249 12.7031L5.49203 12.8152C5.43588 12.7031 5.49203 12.4235 5.68808 12.3673L6.19248 12.2276V6.71226L5.49215 6.65615C5.43599 6.40392 5.57587 6.04029 5.96841 6.01205L8.04196 5.87229L10.9 10.2398V6.37615L10.1713 6.29251C10.1154 5.98418 10.3392 5.76029 10.6195 5.73252L12.5534 5.61996ZM1.96131 1.42092L9.94726 0.832827C10.928 0.748715 11.1803 0.805058 11.7967 1.25281L14.3458 3.04451C14.7665 3.35262 14.9067 3.4365 14.9067 3.77237V13.5992C14.9067 14.215 14.6823 14.5793 13.8979 14.635L4.6239 15.1951C4.03509 15.2231 3.75485 15.1392 3.4465 14.747L1.56922 12.3113C1.23284 11.863 1.09296 11.5276 1.09296 11.1351V2.40043C1.09296 1.89679 1.31736 1.47669 1.96131 1.42092Z" fill="currentColor" />
  </svg>;

export const LinearLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path d="M1.17156 9.61319C1.14041 9.4804 1.2986 9.39676 1.39505 9.49321L6.50679 14.6049C6.60323 14.7014 6.5196 14.8596 6.38681 14.8284C3.80721 14.2233 1.77669 12.1928 1.17156 9.61319ZM1.00026 7.56447C0.997795 7.60413 1.01271 7.64286 1.0408 7.67096L8.32904 14.9592C8.35714 14.9873 8.39586 15.0022 8.43553 14.9997C8.76721 14.9791 9.09266 14.9353 9.41026 14.8701C9.51729 14.8481 9.55448 14.7166 9.47721 14.6394L1.36063 6.52279C1.28337 6.44552 1.15187 6.48271 1.12989 6.58974C1.06466 6.90734 1.02092 7.23278 1.00026 7.56447ZM1.58953 5.15875C1.56622 5.21109 1.57809 5.27224 1.6186 5.31275L10.6872 14.3814C10.7278 14.4219 10.7889 14.4338 10.8412 14.4105C11.0913 14.2991 11.3336 14.1735 11.5672 14.0347C11.6445 13.9888 11.6564 13.8826 11.5929 13.819L2.18099 4.40714C2.11742 4.34356 2.01121 4.35549 1.96529 4.43278C1.8265 4.66636 1.70091 4.9087 1.58953 5.15875ZM2.77222 3.53036C2.7204 3.47854 2.7172 3.39544 2.76602 3.34079C4.04913 1.9043 5.9156 1 7.99327 1C11.863 1 15 4.13702 15 8.00673C15 10.0844 14.0957 11.9509 12.6592 13.234C12.6046 13.2828 12.5215 13.2796 12.4696 13.2278L2.77222 3.53036Z" fill="currentColor" />
  </svg>;

export const GitHubLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path fill-rule="evenodd" clip-rule="evenodd" d="M7.49933 0.25C3.49635 0.25 0.25 3.49593 0.25 7.50024C0.25 10.703 2.32715 13.4206 5.2081 14.3797C5.57084 14.446 5.70302 14.2222 5.70302 14.0299C5.70302 13.8576 5.69679 13.4019 5.69323 12.797C3.67661 13.235 3.25112 11.825 3.25112 11.825C2.92132 10.9874 2.44599 10.7644 2.44599 10.7644C1.78773 10.3149 2.49584 10.3238 2.49584 10.3238C3.22353 10.375 3.60629 11.0711 3.60629 11.0711C4.25298 12.1788 5.30335 11.8588 5.71638 11.6732C5.78225 11.205 5.96962 10.8854 6.17658 10.7043C4.56675 10.5209 2.87415 9.89918 2.87415 7.12104C2.87415 6.32925 3.15677 5.68257 3.62053 5.17563C3.54576 4.99226 3.29697 4.25521 3.69174 3.25691C3.69174 3.25691 4.30015 3.06196 5.68522 3.99973C6.26337 3.83906 6.8838 3.75895 7.50022 3.75583C8.1162 3.75895 8.73619 3.83906 9.31523 3.99973C10.6994 3.06196 11.3069 3.25691 11.3069 3.25691C11.7026 4.25521 11.4538 4.99226 11.3795 5.17563C11.8441 5.68257 12.1245 6.32925 12.1245 7.12104C12.1245 9.9063 10.4292 10.5192 8.81452 10.6985C9.07444 10.9224 9.30633 11.3648 9.30633 12.0413C9.30633 13.0102 9.29742 13.7922 9.29742 14.0299C9.29742 14.2239 9.42828 14.4496 9.79591 14.3788C12.6746 13.4179 14.75 10.7025 14.75 7.50024C14.75 3.49593 11.5036 0.25 7.49933 0.25Z" fill="currentColor" />
  </svg>;

## About Agent Integrations

Augment Agent can access external services through integrations to add additional context to your requests and take actions on your behalf. These integrations allow Augment Agent to seamlessly work with your development tools without leaving your editor.

Once set up, Augment Agent will automatically use the appropriate integration based on your request context. Or, you can always mention the service in your request to use the integration.

## Setting Up Integrations

To set up integrations with Augment Agent in VS Code, follow these steps:

1. Click the settings icon in the top right of Augment's chat window or press <Keyboard shortcut="Cmd/Ctrl Shift P" /> and select <Command text="Show Settings Panel" />
2. Click "Connect" for the integration you want to set up

<img className="block rounded-xl" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=89a56ce1b2adfceeff53aa5c2c7e1e3d" alt="Set up integrations in the settings page" width="1096" height="598" data-path="images/integration-settings.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=280&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=340403281e17bb92431e2d8256147913 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=560&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5181e8e7a090238dc17c4bf037af62a4 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=840&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f3549289d4e1246092e524dbd7a012fc 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=1100&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=edf707f8b5706d828f47005b842d574e 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=1650&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a17cb3a8b511caeb927cd707398e4c28 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/integration-settings.png?w=2500&maxW=1096&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8863d6e3a97b999eada3abab0279cc82 2500w" data-optimize="true" data-opv="2" />

You'll be redirected to authorize the integration with the appropriate service. After authorization, the integration will be available for use with Augment Agent.

## Native Integrations

## <div className="flex items-center gap-2"><div className="w-6 h-6"><GitHubLogo /></div> GitHub Integration</div>

Add additional context to your requests and take actions. Pull in information from a GitHub Issue, make the changes to your code (or have Agent do it for you), and open a Pull Request all without leaving your editor.

### Examples

* "Implement Issue #123 and open up a pull request"
* "Find all issues assigned to me"
* "Check the CI status of my latest commit"

For authorization details, see [GitHub documentation](https://docs.github.com/en/apps/oauth-apps/using-oauth-apps/authorizing-oauth-apps).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><LinearLogo /></div> Linear Integration</div>

Read, update, comment on, and resolve your Linear issues within your IDE.

### Examples

* "Fix TES-1"
* "Create Linear tickets for these TODOs"
* "Help me triage these new bug reports"

For authorization details, see [Linear documentation](https://linear.app/docs/third-party-application-approvals).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><JiraLogo /></div> Jira Integration</div>

Work on your Jira issues, create new tickets, and update existing ones.

### Examples

* "Show me all my assigned Jira tickets"
* "Create a Jira ticket for this bug"
* "Create a PR to fix SOF-123"
* "Update the status of PROJ-123 to 'In Progress'"

For authorization details, see [Jira documentation](https://support.atlassian.com/jira-software-cloud/docs/allow-oauth-access/).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><ConfluenceLogo /></div> Confluence Integration</div>

Query existing documentation or update pages directly from your IDE. Ensure your team's knowledge base stays current without any context switching.

### Examples

* "Summarize our Confluence page on microservice architecture"
* "Find information about our release process in Confluence"
* "Update our onboarding docs to explain how we use Bazel"

For authorization details, see [Confluence documentation](https://developer.atlassian.com/cloud/confluence/oauth-2-3lo-apps/).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><NotionLogo /></div> Notion Integration</div>

Search and retrieve information from your team's knowledge base - access documentation, meeting notes, and project specifications. This integration is currently READ-ONLY.

### Examples

* "Find Notion pages about our API documentation"
* "Show me the technical specs for the payment system"
* "What outstanding tasks are left from yesterday's team meeting?"

For authorization details, see [Notion documentation](https://www.notion.so/help/add-and-manage-connections-with-the-api#install-from-a-developer).

## <div className="flex items-center gap-2"><div className="w-6 h-6"><GleanLogo /></div> Glean Integration</div>

> **Note:** The Glean integration is in early access and thus is a little different from other integrations.
>
> * It is currently only available to enterprise customers.
> * It does not appear in the list of integrations in the settings panel.

The Glean integration lets the agent retrieve information from your team's internal data sources leveraging Glean's powerful search engine.

**To Enable the Glean Integration:** You'll need to be have administrator access to Augment and Glean. Follow the instructions on [https://app.augmentcode.com/dashboard/glean](https://app.augmentcode.com/dashboard/glean) and your agent will be ready to use Glean!

### Examples

* "Search Glean for past related incidents and how they were resolved"
* "Search Glean for why we're migrating to a new payment processor"

## Enhanced Native Integrations

> **New:** Enhanced native integrations for Sentry and Stripe launched on July 30, 2025, providing deeper, more seamless access to your error tracking and payment data.

### <div className="flex items-center gap-2"><div className="w-6 h-6"><SentryLogo /></div> Sentry Integration</div>

Search issues, errors, traces, logs, and releases. Create RCAs and AI-Generated fixes with Seer integration for comprehensive error tracking and resolution.

#### Examples

* "Diagnose the top unresolved crashes in my React Native app and propose fixes"
* "Show me all errors from the latest release and their impact"
* "Create a root cause analysis for the payment processing errors"
* "Find similar issues that were resolved and suggest fixes"

### <div className="flex items-center gap-2"><div className="w-6 h-6"><StripeLogo /></div> Stripe Integration</div>

Real-time payment events, refund status, subscription metrics, and secure tokenization. Available via both remote and local MCP servers with OAuth MCP support in public preview.

#### Examples

* "Create a dashboard showing failed payment intents in the last 24 hours and suggest retry logic"
* "Analyze subscription churn patterns and recommend retention strategies"
* "Show me all refunds processed this week and their reasons"
* "Generate a report on payment method performance"

## Next Steps

* [Configure additional tools with Easy MCP or advanced MCP setup](/setup-augment/mcp)
* Explore one-click integrations for CircleCI, MongoDB, and Redis through Easy MCP


# Rules & Guidelines for Agent and Chat
Source: https://docs.augmentcode.com/setup-augment/guidelines

You can provide custom rules and guidelines written in natural language to improve Agent and Chat with your preferences, best practices, styles, and technology stack.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Availability = ({tags}) => {
  const tagTypes = {
    invite: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    beta: {
      styles: "border border-zinc-500/20 bg-zinc-50/50 dark:border-zinc-500/30 dark:bg-zinc-500/10 text-zinc-900 dark:text-zinc-200"
    },
    vscode: {
      styles: "border border-sky-500/20 bg-sky-50/50 dark:border-sky-500/30 dark:bg-sky-500/10 text-sky-900 dark:text-sky-200"
    },
    jetbrains: {
      styles: "border border-amber-500/20 bg-amber-50/50 dark:border-amber-500/30 dark:bg-amber-500/10 text-amber-900 dark:text-amber-200"
    },
    vim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    neovim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    default: {
      styles: "bg-gray-200"
    }
  };
  return <div className="flex items-center space-x-2 border-b pb-4 border-gray-200 dark:border-white/10">
      <span className="text-sm font-medium">Availability</span>
      {tags.map(tag => {
    const tagType = tagTypes[tag] || tagTypes.default;
    return <div key={tag} className={`px-2 py-0.5 rounded-md text-xs font-medium ${tagType.styles}`}>
            {tag}
          </div>;
  })}
    </div>;
};

<Availability tags={["vscode", "jetbrains"]} />

## What are Rules & Guidelines?

Agent and Chat rules and guidelines are natural language instructions that can help Augment reply with more accurate and relevant responses. Rules and guidelines are perfect for telling Augment to take into consideration specific preferences, package versions, styles, and other implementation details that can’t be managed with a linter or compiler. You can create guidelines for a specific workspace or globally for all chats in your IDE; guidelines do not currently apply to Completions, Instructions, or Next Edit.

User Guidelines are defined under Settings and stored within your IDE to be used to guide preferences inside of the Agent and Chat. Workspace Guidelines and Rules are stored directly in your repository.

## Working with User Guidelines

<Info>
  User Guidelines are stored locally in your IDE and will be applied to all future chats in that IDE. Guidelines defined in VSCode will not propagate to JetBrains IDEs and vice versa.
</Info>

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/user-guidelines.png?maxW=1248&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=7167df16f82280f63a8c8c3bb4b12884" alt="Adding user guidelines" className="rounded-xl" width="1248" height="603" data-path="images/user-guidelines.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/user-guidelines.png?w=280&maxW=1248&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=6fc9b2d86f0ec2596a0fdee8813c0d5b 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/user-guidelines.png?w=560&maxW=1248&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=0ac64773f1f94fa570441944b1aa3309 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/user-guidelines.png?w=840&maxW=1248&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=ef0c149e8f9a249d965c7d55cd130d8a 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/user-guidelines.png?w=1100&maxW=1248&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=7afd799667ced4ff5c1e7fe032b78479 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/user-guidelines.png?w=1650&maxW=1248&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a15107ec60bd3b7137cf6f59ca3262ec 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/user-guidelines.png?w=2500&maxW=1248&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=8e7c7746525e11bea6eac4c0d855fe2f 2500w" data-optimize="true" data-opv="2" />

You can add user guidelines by clicking Context menu (@), starting an @-mention inside Chat, or clicking Settings > Rules and User Guidelines.

### Navigating from the Context menu (@) User Guidelines

1. @ mention and select `User Guidelines`
2. Enter your guidelines (see below for tips)
3. Press Escape to save or wait for autosave

### Navigating from Settings > User Guidelines and Rules

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/open-rules.gif?maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=50abbbf49e8cc70847e89e813d39bdf3" alt="Open rules and guidelines" className="rounded-xl" width="800" height="393" data-path="images/open-rules.gif" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/open-rules.gif?w=280&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=0d120443d15268d07bfc4960e704ba72 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/open-rules.gif?w=560&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=245b7235c8babefbfa4ee13562574790 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/open-rules.gif?w=840&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d41b8a8d2d27eec82d53481488fc0c6e 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/open-rules.gif?w=1100&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4adc3ca01c31e0622366119c3f606780 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/open-rules.gif?w=1650&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b610fb0f5e5bdd889c617827bf7b8aa1 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/open-rules.gif?w=2500&maxW=800&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=aae8b4ac46089115f325200fe8e85c9b 2500w" data-optimize="true" data-opv="2" />

1. In the top right corner, select the hamburger menu (⋯)
2. Select Settings
3. From the left menu in Augment Settings, select User Guidelines and Rules

## Working with Rules

You can craft Rules to guide Augment towards specific documentation, frameworks, workflows or workstyles.

Rules are files that live in the `.augment/rules` directory. Currently, we support 3 types of rules:

* **Always**: contents will be included in every user message
* **Manual**: needs to be tagged through @ attaching the Rules file manually
* **Auto**: Agent will automatically detect and attach rules based on a description field

### Importing Rules

**Augment** will automatically import rules if they are detected in the current workspace. Augment will look for markdown files, e.g., files ending with `*.md` or `*.mdx`. You can also manually import rules inside of Settings > Import rules.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/import-rules.png?maxW=1600&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6a44bc0077f7f33d612ec9b71c96a5c2" alt="Import rules" className="rounded-xl" width="1600" height="839" data-path="images/import-rules.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/import-rules.png?w=280&maxW=1600&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c9925376c7966e25e896ea4425eebd95 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/import-rules.png?w=560&maxW=1600&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=66bfcf45b9c7d1d1e9754cc2fbcdcd6d 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/import-rules.png?w=840&maxW=1600&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d89ce345cb8c1013f666b227c5b30954 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/import-rules.png?w=1100&maxW=1600&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=291013f952f380ca777335548b793264 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/import-rules.png?w=1650&maxW=1600&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=22a60fd36ce0e9b7343677e3d1036a50 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/import-rules.png?w=2500&maxW=1600&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a7a647a4dccb5b746b98b8b3c8f937af 2500w" data-optimize="true" data-opv="2" />

### Importing Augment Memories into Rules or User Guidelines

Augment Memories are automatically created by the Agent. If you’ve ever modified the Memories or prompted the Agent to remember something you can import these preferences as Rules or User Guidelines.

1. From the prompt box, click on Augment Memories
2. Select the item you'd like to import and then click User Guidelines at the top of Augment Memories from inside the editor.
3. To add the memory as a Rule, you'll first need to add at least one rule using +Create new rule file. Now, you can select any information inside the Augment Memories and save it as a Rule.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/move-memories.png?maxW=1816&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=71643e2c7d047429b8facd2e78124898" alt="Move memories" className="rounded-xl" width="1816" height="426" data-path="images/move-memories.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/move-memories.png?w=280&maxW=1816&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=72a4c27ebc47a45745f0a4ed49da1b4f 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/move-memories.png?w=560&maxW=1816&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1222aab8a97e76e5899e1f98f083cb55 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/move-memories.png?w=840&maxW=1816&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=69ccb1b8c333620c708df599fdd40036 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/move-memories.png?w=1100&maxW=1816&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ea118890b9a4e6ccc2327d7f0a810cc5 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/move-memories.png?w=1650&maxW=1816&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=03ac0f0272f2f516e1eb6f4d5ce8008c 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/move-memories.png?w=2500&maxW=1816&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4dbf367b8c9fe3babd55b1908fa8a6be 2500w" data-optimize="true" data-opv="2" />

## Working with Workspace Guidelines `.augment-guidelines` (legacy)

You can add an `.augment-guidelines` file to the root of a repository to specify a set of guidelines that Augment will follow for all Agent and Chat sessions on the codebase. The `.augment-guidelines` file should be added to your version control system so that everyone working on the codebase has the same guidelines.

### Tips for good rules and guidelines

* Provide guidelines as a list
* Use simple, clear, and concise language for your guidelines
* Asking for shorter or code-only answers may hurt response quality

### Examples

<AccordionGroup>
  <Accordion title="User Guideline Examples">
    * Ask for additional explanation e.g. `For Typescript code, explain what the code is doing in more detail`

    * Set a preferred language e.g. `Respond to questions in Spanish`
  </Accordion>

  <Accordion title="Rule Examples">
    * Add links to Google Docs, Notion or Confluence files that define goals, product requirements, or project objectives

    * Point to specific documentation e.g. `Python 3.13.5` for the dependencies inside your project

    * Outline templates or example code commonly used in your project

    * Establish consistent frameworks, coding styles, and architectural patterns across your codebase

    * Provide examples on codebase style. For example:
      * Information that ONLY applies to the specific files, functions, or code snippets
      * Vague or obvious preferences that aren't actionable
      * General statements about good programming practices that any user would want
  </Accordion>

  <Accordion title="Workspace Guideline Examples">
    * Identifying preferred libraries e.g. `pytest vs unittest`
    * Identifying specific patterns e.g. `For NextJS, use the App Router and server components`
    * Rejecting specific anti-patterns e.g. `a deprecated internal module`
    * Defining naming conventions e.g. `functions start with verbs`
  </Accordion>
</AccordionGroup>

## FAQs

<AccordionGroup>
  <Accordion title="How are Rules different from Guidelines?">
    Guidelines and Rules differ in how they are stored and their scope of influence.

    * **User Guidelines** are stored in the user’s local IDE storage that will persist across Chat & Agent sessions; however, they do not persist across workspaces.
    * **Rules** will also be stored within the repository under the `.augment/rules` root that will allow you to split up previous Guidelines into multiple files to more precisely define your preferences.
    * **Workspace Guidelines** (legacy) stored within the repository under the `.augment-guidelines` file are a legacy set of rules that can be edited by editing the `.augment-guidelines` in your repository. Augment will automatically import Workspace Guidelines as Rules which you can access under Settings > User Guidelines and Rules.
  </Accordion>

  <Accordion title="What are the current limitations?">
    * User Guidelines are currently limited to a maximum of 24,576 characters.
    * Workspace Guidelines + Rules are limited to a maximum of 49,512 characters. If we exceed these limits, the user will be notified in app and be applied in order of (manual rules, always + auto rules, .augment-guidelines)
    * For VSCode, Guidelines are available in plugin version 0.492.0 and above
    * For JetBrains IDEs, Guidelines are available in plugin version 0.197.0 and above
    * Rules are not yet available in JetBrains IDEs
  </Accordion>
</AccordionGroup>


# Install Augment for Slack
Source: https://docs.augmentcode.com/setup-augment/install-slack-app

Ask Augment questions about your codebase right in Slack.

export const Next = ({children}) => <div className="border-t border-b pb-8 border-gray dark:border-white/10">
    <h3>Next steps</h3>
    {children}
  </div>;

export const SlackLogo = () => <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 127 127">
    <path fill="#E01E5A" d="M27.2 80c0 7.3-5.9 13.2-13.2 13.2C6.7 93.2.8 87.3.8 80c0-7.3 5.9-13.2 13.2-13.2h13.2V80zm6.6 0c0-7.3 5.9-13.2 13.2-13.2 7.3 0 13.2 5.9 13.2 13.2v33c0 7.3-5.9 13.2-13.2 13.2-7.3 0-13.2-5.9-13.2-13.2V80z" />
    <path fill="#36C5F0" d="M47 27c-7.3 0-13.2-5.9-13.2-13.2C33.8 6.5 39.7.6 47 .6c7.3 0 13.2 5.9 13.2 13.2V27H47zm0 6.7c7.3 0 13.2 5.9 13.2 13.2 0 7.3-5.9 13.2-13.2 13.2H13.9C6.6 60.1.7 54.2.7 46.9c0-7.3 5.9-13.2 13.2-13.2H47z" />
    <path fill="#2EB67D" d="M99.9 46.9c0-7.3 5.9-13.2 13.2-13.2 7.3 0 13.2 5.9 13.2 13.2 0 7.3-5.9 13.2-13.2 13.2H99.9V46.9zm-6.6 0c0 7.3-5.9 13.2-13.2 13.2-7.3 0-13.2-5.9-13.2-13.2V13.8C66.9 6.5 72.8.6 80.1.6c7.3 0 13.2 5.9 13.2 13.2v33.1z" />
    <path fill="#ECB22E" d="M80.1 99.8c7.3 0 13.2 5.9 13.2 13.2 0 7.3-5.9 13.2-13.2 13.2-7.3 0-13.2-5.9-13.2-13.2V99.8h13.2zm0-6.6c-7.3 0-13.2-5.9-13.2-13.2 0-7.3 5.9-13.2 13.2-13.2h33.1c7.3 0 13.2 5.9 13.2 13.2 0 7.3-5.9 13.2-13.2 13.2H80.1z" />
  </svg>;

export const GitHubLogo = () => <svg width="24" height="24" viewBox="0 0 15 15" fill="none" xmlns="http://www.w3.org/2000/svg">
    <path fill-rule="evenodd" clip-rule="evenodd" d="M7.49933 0.25C3.49635 0.25 0.25 3.49593 0.25 7.50024C0.25 10.703 2.32715 13.4206 5.2081 14.3797C5.57084 14.446 5.70302 14.2222 5.70302 14.0299C5.70302 13.8576 5.69679 13.4019 5.69323 12.797C3.67661 13.235 3.25112 11.825 3.25112 11.825C2.92132 10.9874 2.44599 10.7644 2.44599 10.7644C1.78773 10.3149 2.49584 10.3238 2.49584 10.3238C3.22353 10.375 3.60629 11.0711 3.60629 11.0711C4.25298 12.1788 5.30335 11.8588 5.71638 11.6732C5.78225 11.205 5.96962 10.8854 6.17658 10.7043C4.56675 10.5209 2.87415 9.89918 2.87415 7.12104C2.87415 6.32925 3.15677 5.68257 3.62053 5.17563C3.54576 4.99226 3.29697 4.25521 3.69174 3.25691C3.69174 3.25691 4.30015 3.06196 5.68522 3.99973C6.26337 3.83906 6.8838 3.75895 7.50022 3.75583C8.1162 3.75895 8.73619 3.83906 9.31523 3.99973C10.6994 3.06196 11.3069 3.25691 11.3069 3.25691C11.7026 4.25521 11.4538 4.99226 11.3795 5.17563C11.8441 5.68257 12.1245 6.32925 12.1245 7.12104C12.1245 9.9063 10.4292 10.5192 8.81452 10.6985C9.07444 10.9224 9.30633 11.3648 9.30633 12.0413C9.30633 13.0102 9.29742 13.7922 9.29742 14.0299C9.29742 14.2239 9.42828 14.4496 9.79591 14.3788C12.6746 13.4179 14.75 10.7025 14.75 7.50024C14.75 3.49593 11.5036 0.25 7.49933 0.25Z" fill="currentColor" />
  </svg>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

<Note>
  The Augment GitHub App is compatible with GitHub.com and GitHub Enterprise Cloud. GitHub Enterprise Server is not currently supported.
</Note>

## About Augment for Slack

Augment for Slack brings the power of Augment Chat to your team's Slack workspace. Mention <Command text="@Augment" /> in any channel or start a DM with Augment to have deep codebase-aware conversations with your team.

*To protect your confidential information, Augment will not include repository context in responses when used in shared channels with external members.*

## Installing Augment for Slack

### 1. Install GitHub App

<CardGroup cols={1}>
  <Card title="Install Augment GitHub App" href="https://github.com/apps/augmentcode/installations/new" icon={<GitHubLogo />} horizontal>
    GitHub App for Augment Chat in Slack
  </Card>
</CardGroup>

To enable Augment's rich codebase-awareness, install the Augment GitHub App and grant access to your desired repositories. Organization owners and repository admins can install the app directly; others will need owner approval. See [GitHub documentation](https://docs.github.com/en/apps/using-github-apps/installing-a-github-app-from-a-third-party) for details.

We recommend authorizing only the few active repositories you want accessible to Augment Slack users. You can modify repository access anytime in the GitHub App settings.

<img className="block rounded-xl" src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/install-github-app.png?maxW=1372&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=cbb3c89179671d99717de0a46f951020" alt="Installing the GitHub app on a single repository" width="1372" height="1387" data-path="images/install-github-app.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/install-github-app.png?w=280&maxW=1372&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=fc59ee6f9dcb1c4384f711f4d3bae25a 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/install-github-app.png?w=560&maxW=1372&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=29c3e593ef6f159f88165c3854b79e95 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/install-github-app.png?w=840&maxW=1372&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6e122873e9b554cae9763c5e89dd8d45 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/install-github-app.png?w=1100&maxW=1372&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a1470779744450e283441255a0037c3f 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/install-github-app.png?w=1650&maxW=1372&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=42294e5b6781f02056e97bd059373d4e 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/install-github-app.png?w=2500&maxW=1372&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=07120c9e4de21be01c917d85a6771a04 2500w" data-optimize="true" data-opv="2" />

### 2. Install Slack App

<CardGroup cols={1}>
  <Card title="Install Augment for Slack" href="https://slack.com/oauth/v2/authorize?client_id=3751018318864.7878669571030&scope=app_mentions:read,channels:history,channels:read,chat:write,groups:history,groups:read,im:history,im:read,im:write,mpim:history,mpim:read,mpim:write,reactions:read,reactions:write,users.profile:read,users:read,users:read.email,groups:write,commands,assistant:write&user_scope=identity.basic" icon={<SlackLogo />} horizontal>
    Slack App for Augment Code
  </Card>
</CardGroup>

Once you have the GitHub App installed, install the Augment Slack App. You'll need an Augment account and correct permissions to install Slack apps for your workspace.

Any workspace member can use the Slack app once installed. Contact us if you need to restrict access to specific channels or users.

### 3. Add Augment to the Slack Navigation Bar

Make Augment easily accessible by adding it to Slack's assistant-view navigation bar:

1. Click your profile picture → **Preferences** → **Navigation**
2. Under **App agents & assistants**, select **Augment**

*Note: Each user can customize this setting in their preferences.*

<Next>
  [Using Augment for Slack](/using-augment/slack)
</Next>


# Install Augment for Visual Studio Code
Source: https://docs.augmentcode.com/setup-augment/install-visual-studio-code

Augment in Visual Studio Code gives you powerful code completions, transformations, and chat capabilities integrated into your favorite code editor.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const VscodeLogo = () => <svg xmlns="http://www.w3.org/2000/svg" xmlnsXlink="http://www.w3.org/1999/xlink" version="1.1" viewBox="0 0 64 64">
    <defs>
      <mask id="mask" x=".5" y=".7" width="63.5" height="63.1" maskUnits="userSpaceOnUse">
        <g id="mask0">
          <path fill="#fff" d="M45.5,63.5c1,.4,2.1.4,3.1-.1l13.1-6.3c1.4-.7,2.2-2,2.2-3.6V10.9c0-1.5-.9-2.9-2.2-3.6l-13.1-6.3c-1.3-.6-2.9-.5-4,.4-.2.1-.3.3-.5.4l-25,22.8-10.9-8.3c-1-.8-2.4-.7-3.4.2l-3.5,3.2c-1.2,1-1.2,2.9,0,3.9l9.4,8.6L1.4,40.9c-1.2,1-1.1,2.9,0,3.9l3.5,3.2c.9.9,2.4.9,3.4.1l10.9-8.3,25,22.8c.4.4.9.7,1.4.9ZM48.1,17.9l-19,14.4,19,14.4v-28.8Z" />
        </g>
      </mask>
      <linearGradient id="linear-gradient" x1="32.2" y1="65.3" x2="32.2" y2="2.2" gradientTransform="translate(0 66) scale(1 -1)" gradientUnits="userSpaceOnUse">
        <stop offset="0" stopColor="#fff" />
        <stop offset="1" stopColor="#fff" stopOpacity="0" />
      </linearGradient>
    </defs>
    <g style={{
  isolation: "isolate"
}}>
      <g mask="url(#mask)">
        <path fill="#0065a9" d="M61.8,7.4l-13.1-6.3c-1.5-.7-3.3-.4-4.5.8L1.4,40.9c-1.2,1-1.1,2.9,0,3.9l3.5,3.2c.9.9,2.4.9,3.4.2L59.8,9c1.7-1.3,4.2,0,4.2,2.1v-.2c0-1.5-.9-2.9-2.2-3.6Z" />
        <path fill="#007acc" d="M61.8,57.1l-13.1,6.3c-1.5.7-3.3.4-4.5-.8L1.4,23.6c-1.2-1-1.1-2.9,0-3.9l3.5-3.2c.9-.9,2.4-.9,3.4-.2l51.5,39.1c1.7,1.3,4.2,0,4.2-2.1v.2c0,1.5-.9,2.9-2.2,3.6Z" />
        <path fill="#1f9cf0" d="M48.7,63.4c-1.5.7-3.3.4-4.5-.8,1.5,1.5,4,.4,4-1.6V3.5c0-2.1-2.5-3.1-4-1.6,1.2-1.2,3-1.5,4.5-.8l13.1,6.3c1.4.7,2.2,2,2.2,3.6v42.6c0,1.5-.9,2.9-2.2,3.6l-13.1,6.3Z" />
        <g style={{
  mixBlendMode: "overlay",
  opacity: 0.2
}}>
          <path fill="url(#linear-gradient)" fillRule="evenodd" d="M45.5,63.5c1,.4,2.1.4,3.1-.1l13.1-6.3c1.4-.7,2.2-2,2.2-3.6V10.9c0-1.5-.9-2.9-2.2-3.6l-13.1-6.3c-1.3-.6-2.9-.5-4,.4-.2.1-.3.3-.5.4l-25,22.8-10.9-8.3c-1-.8-2.4-.7-3.4.1l-3.5,3.2c-1.2,1-1.2,2.9,0,3.9l9.4,8.6L1.4,40.9c-1.2,1-1.1,2.9,0,3.9l3.5,3.2c.9.9,2.4.9,3.4.2l10.9-8.3,25,22.8c.4.4.9.7,1.4.9ZM48.1,17.9l-19,14.4,19,14.4v-28.8Z" />
        </g>
      </g>
    </g>
  </svg>;

export const ExternalLink = ({text, href}) => <a href={href} rel="noopener noreferrer">
    {text}
  </a>;

<CardGroup cols={1}>
  <Card title="Get the Augment Extension" href="https://marketplace.visualstudio.com/items?itemName=augment.vscode-augment" icon={<VscodeLogo />} horizontal>
    Install Augment for Visual Studio Code
  </Card>
</CardGroup>

## About Installation

Installing <ExternalLink text="Augment for Visual Studio Code" href="https://marketplace.visualstudio.com/items?itemName=augment.vscode-augment" /> is easy and will take you less than a minute. You can install the extension directly from the Visual Studio Code Marketplace or follow the instructions below.

<img className="block rounded-xl" src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-extension.png?maxW=1691&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=73ba7429f69a76c9707cc2d844484111" alt="Augment extension in Visual Studio Code Marketplace" width="1691" height="807" data-path="images/vscode-extension.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-extension.png?w=280&maxW=1691&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=28f41a3f4de62a8e5d85bbab37f0dc71 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-extension.png?w=560&maxW=1691&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=ff7cbad8bfdc03220555f19a04f8f2b2 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-extension.png?w=840&maxW=1691&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b0c68c0cf3ef4d44b7848bb4033453ed 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-extension.png?w=1100&maxW=1691&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3ee5db5c05c324bf24e31ab550613cd0 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-extension.png?w=1650&maxW=1691&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d6a87a2abb720662514b317a1a157b51 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/vscode-extension.png?w=2500&maxW=1691&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a9ada52c26ad3239f92c798f3de6036b 2500w" data-optimize="true" data-opv="2" />

## Installing Augment for Visual Studio Code

<Steps>
  <Step title="Make sure you have the latest version of Visual Studio Code installed">
    You can download the latest version of Visual Studio Code from the <ExternalLink text="Visual Studio Code website" href="https://code.visualstudio.com/" />. If you already have Visual Studio Code installed, you can update to the latest version by going to <Command text="Code > Check for Updates..." />.
  </Step>

  <Step title="Open the Extensions panel in Visual Studio Code">
    Click the Extensions icon in the sidebar to show
    the Extensions panel.
  </Step>

  <Step title="Search for Augment in the marketplace">
    Using the search bar in the Extensions panel, search for{" "}
    <Command text="Augment" />.
  </Step>

  <Step title="Install the extension">
    Click <Command text="Install" /> to install the extension.
  </Step>

  <Step title="Sign into Augment and get coding">
    Sign in to by clicking <Command text="Sign in to Augment" /> in the Augment
    panel. If you do not see the Augment panel, use the shortcut{" "}
    <Keyboard shortcut="Cmd/Ctrl L" /> or click the Augment icon{" "}
    <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c45fb0199a88c329cbfad5e2d0c225a1" className="inline h-3 p-0 m-0" width="18" height="12" data-path="images/augment-icon-simple.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=280&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8b6cc675b3b75b7896bd431f64a092a0 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=560&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4c6ce1c701082b4f77e38ab0328a9f30 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=840&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8b8a4c9d542987cc6b15dae04d718a95 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=1100&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0d07791cb30b119aa46e3b4d6006628c 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=1650&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9a24403942c20bdfc300b06276e49f56 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-simple.svg?w=2500&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f6bb21ac056e042477613841f39510b4 2500w" data-optimize="true" data-opv="2" /> in the side bar of your IDE. See more details in [Sign
    In](/setup-augment/sign-in).
  </Step>
</Steps>

## About pre-release versions

We regularly publish pre-release versions of the Augment extension. To use the pre-release version, go to the Augment extension in the Extensions panel and click <Command text="Switch to Pre-Release Version" /> and then <Command text="Restart extensions" />.

Pre-release versions may sometimes contain bugs or otherwise be unstable. As with the released version, please report any problems by sending us [feedback](/troubleshooting/feedback).


# Setup Model Context Protocol servers
Source: https://docs.augmentcode.com/setup-augment/mcp

Use Model Context Protocol (MCP) servers with Augment to expand Augment's capabilities with external tools and data sources.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## About Model Context Protocol servers

Augment Agent can utilize external integrations through Model Context Protocol (MCP) to access external systems for information and integrate tools to take actions. MCP is an open protocol that provides a standardized way to connect AI models to different data sources and tools. MCP servers can be used to access local or remote databases, run automated browser testing, send messages to Slack, or even play music on Spotify.

## Easy MCP: One-Click Integrations

> **New:** Easy MCP launched on July 30, 2025, making it easier than ever to connect popular developer tools to Augment Code.

Easy MCP is a new feature in the Augment Code extension that transforms complex MCP server setup into a single click. Instead of manually configuring servers, hunting for GitHub repos, or editing JSON files, you can now connect popular developer tools with just an API token or OAuth approval.

### Available Easy MCP Integrations

Easy MCP provides one-click access to these popular developer tools:

#### CircleCI

* **Context:** Build logs, test insights, flaky-test detection
* **Sample prompt:** "Find the latest failed pipeline on my branch and surface the failing tests."
* **Setup:** Click "+", paste your CircleCI API token, and you're connected.

#### MongoDB

* **Context:** Data exploration, database management, and context-aware code generation
* **Sample prompt:** "Analyze my user collection schema and suggest optimizations for our new search feature."
* **Setup:** One-click OAuth connection to your MongoDB instance.

#### Redis

* **Context:** Keyspace introspection, TTL audits, and migration helpers
* **Sample prompt:** "Generate a migration script to move expiring session keys to the new namespace."
* **Setup:** Connect with your Redis credentials in seconds.

#### Honeycomb

* **Context:** Ingest traces, spans, and query results for instant observability in your coding loop
* **Sample prompt:** "Show me recent slow traces in production and suggest where to add instrumentation."
* **Setup:** Click Connect under Honeycomb, complete OAuth sign-in and grant required scopes, select organization/environment (if prompted), verify connection by running a quick query from within the IDE.

#### Heroku

* **Context:** Pull dyno statuses, release histories, and live logs into your IDE
* **Sample prompt:** "Show the most recent release for staging and highlight any errors in the logs."
* **Setup:** Ensure Heroku CLI is installed and you're logged in locally, click Connect under Heroku, select the app(s) you want to access, verify by fetching recent releases or viewing logs.

#### Render

* **Context:** Access build logs, service statuses, and environment details right where you're coding
* **Sample prompt:** "Why did my last staging build fail, and how should I adjust the config?"
* **Setup:** Click Connect under Render, paste in your Render API key and confirm, choose the services/environments to surface, validate by loading the latest build logs.

#### Vercel

* **Context:** Stream deployment previews, build logs, and analytics for faster iteration on web projects
* **Sample prompt:** "What's in the latest preview deployment of my Next.js app, and are there any build errors?"
* **Setup:** Click Connect under Vercel, complete OAuth sign-in and select team/project, grant access to deployments and analytics, verify by asking about the latest preview deployment details.

### Authentication Methods at a Glance

<Callout type="info">
  **Authentication Summary:**

  * **OAuth:** Honeycomb, MongoDB, Vercel
  * **API Key:** CircleCI, Render
  * **CLI-based:** Heroku (requires Heroku CLI)
</Callout>

### Getting Started with Easy MCP

1. Open the Augment Code extension in VS Code
2. Navigate to the Easy MCP pane in the settings
3. Click the "+" button next to your desired integration
4. Paste an API token or approve OAuth
5. Start using the integration immediately in your Agent conversations

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c02010664a36e319631e3f5367f5f00e" className="rounded-xl" width="1078" height="646" data-path="images/EasyMCP.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=280&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b26a28d983527d327bc35e249eabf1a8 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=560&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7e06026e10eefc855da6579dac1dea47 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=840&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3c6df59927adaa82ba7427ad8f0defa2 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=1100&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=849c567deb9a052d933a4aa31f492dec 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=1650&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3e66c48df372bb4e699350f8073ff0c6 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/EasyMCP.png?w=2500&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=cda0cb53a2619c7cb2adffe3a12c3c38 2500w" data-optimize="true" data-opv="2" />

From that moment on, Augment Code streams your tool's live context into every suggestion and autonomous Agent run.

## Advanced MCP Configuration

For developers who need custom MCP server configurations or want to use servers not available through Easy MCP, you can still configure MCP servers manually.

There are three ways to configure MCP servers in Augment:

1. **Easy MCP** (recommended) - One-click integrations for popular tools
2. **Augment Settings Panel** - Manual configuration with a GUI
3. **Import from JSON** - Paste a JSON config to quickly add servers

MCP servers configured through the Settings Panel or Import from JSON are managed in the same place. After importing, you can edit or remove servers in the Settings Panel.

## Configure in the Augment Settings Panel

The easiest way to configure MCP servers is to use the Augment Settings Panel.
To access the settings panel, open the options menu in the upper right of the Augment panel and click the Settings option. Once the settings panel is open, you will see a section for MCP servers.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=f34e3682127f6e6ba2dfc5a4ae7fd8a5" className="rounded-xl" width="1296" height="556" data-path="images/settings-panel-mcp.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a6dff18658e5c7454fa009cc484467db 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=dbc7a07976708c4fc72a662b98c06c60 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e382a538a495053c3ca1a3c01d5e85ba 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=2efdfd04627b5a659795e5b74e672b4d 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d0f3ce6ce06c668a2f3160a35c0586e5 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e4b1e413786735c373fb6ec386cd676e 2500w" data-optimize="true" data-opv="2" />

Fill in the `name` and `command` fields. The `name` field must be a unique name for the server. The `command` field is the command to run the server. Environment variables have their own section and no longer need to be specified in the command.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=20d9ffa2c683194ec1d66afe390f6f9d" className="rounded-xl" width="1090" height="586" data-path="images/mcp-env.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=280&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e9c87679180a6db78e05d7cce22845ff 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=560&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e7e5805c874eb5e006c27ee3f52360fa 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=840&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8930b7ececcdd06705dcc9d9ed86ef12 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=1100&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8e9b4f557196621ab4d45dd52defbda7 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=1650&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=bd0ff7868ab46ea8325a6b9ed1856294 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/mcp-env.png?w=2500&fit=max&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4cba9d7e59969d4a48aa630ab14932a7 2500w" data-optimize="true" data-opv="2" />

To add additional servers, click the `+` button next to the `MCP` header.
To edit a configuration, or to delete a server, click the `...` button next to the server name.

### Add a Remote MCP server

If your MCP server runs remotely (for example, a hosted service), click the "+ Add remote MCP" button in the MCP section. Remote MCP connections support both HTTP and SSE (Server‑Sent Events).

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=21086d1c640c6e20975aa7207532be78" className="rounded-xl" width="1036" height="676" data-path="images/settings-panel-mcp-remote.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3ac00d4975d2791c378a0e24b7fd1457 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4d92460a09146279b73693c6af5be240 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=2a9dfd961063e277d0dee794b71b0b47 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=cdbad5fac2856fe1fb9bc272cb22622d 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d99df8defa992c69589501c7db0e0204 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-remote.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=7f5c7e96f585a368523586154bfd696e 2500w" data-optimize="true" data-opv="2" />

* Connection Type: choose HTTP or SSE
* Name: a unique display name for the server
* URL: the base URL to your MCP server (e.g., [https://api.example.com](https://api.example.com))

Remote MCP servers appear alongside your local MCP servers in the list. You can edit or remove them using the "..." menu next to the server name.

## Import from JSON

You can quickly add MCP servers by importing a JSON configuration from the Augment Settings Panel:

1. Open the Settings Panel (gear icon in the Augment panel)
2. In the MCP section, click <strong>Import from JSON</strong>
3. Paste a configuration like the following and click Save

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-json.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=63f0f66b4c03a744d066509d2bd7d107" className="rounded-xl" width="1018" height="512" data-path="images/settings-panel-mcp-json.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-json.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c92854a977210732f7ce88365f420f13 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-json.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=13f3d3e3bd2ddd45511b24418908e37f 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-json.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d26b8bcf4f9e592bf2b539a469de1dbe 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-json.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=39eed3e27ae9dfeeb394146153648b2a 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-json.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=734fdddd4287a85ee69e6455b1af98b1 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/settings-panel-mcp-json.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=bf906af74ac296b11558e48a07e99caf 2500w" data-optimize="true" data-opv="2" />

**Example: Local command (Context7 via npx)**

```json
{
  "mcpServers": {
    "Context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp"]
    }
  }
}
```

**Example: Remote SSE endpoint**

```json
{
  "mcpServers": {
    "test": {
      "url": "http://localhost:3001/sse",
      "type": "sse"
    }
  }
}
```

After importing, servers appear in the list where you can edit, test, or remove them. Ensure any required dependencies for the server are installed on your machine.

## Server compatibility

Not all MCP servers are compatible with Augment's models. The MCP standard, implementation of specific servers, and Augment's MCP support are frequently being updated, so check compatibility frequently.


# Sign in and out
Source: https://docs.augmentcode.com/setup-augment/sign-in

After you have installed the Augment extension, you will need to sign in to your account.

export const MoreVertIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M479.79-192Q450-192 429-213.21t-21-51Q408-294 429.21-315t51-21Q510-336 531-314.79t21 51Q552-234 530.79-213t-51 21Zm0-216Q450-408 429-429.21t-21-51Q408-510 429.21-531t51-21Q510-552 531-530.79t21 51Q552-450 530.79-429t-51 21Zm0-216Q450-624 429-645.21t-21-51Q408-726 429.21-747t51-21Q510-768 531-746.79t21 51Q552-666 530.79-645t-51 21Z" />
    </svg>
  </div>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## About Authentication

You can sign in to Augment using one of the supported identity providers–Google or Microsoft–or sign in using your email address and a single-use code we send to you. During the process, you will be redirected to your browser to sign in to your account.

## Sign in

<Steps>
  <Step title="Sign in to Augment">
    Click the <Command text="Sign in to Augment" /> button in the Augment panel. If you do not see the Augment panel press <Keyboard shortcut="Cmd/Ctrl L" />. If you are using Visual Studio Code, you be asked to confirm going to Augment's authentication portal.
  </Step>

  <Step title="Sign in with your email">
    In your browser, you may sign in with Google, Microsoft, or by receiving a single-use code in your email.
  </Step>

  <Step title="Accept the terms and conditions">
    If this is the first time you've signed in to Augment, you will be asked to accept the terms and conditions.
  </Step>

  <Step title="Return to your IDE">
    You will be automically redirected back to your IDE and you will see the Augment icon
    change to{" "}
    <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0f98e2222af9b74b38faeb8c56ed09be" className="inline h-3 p-0 m-0" width="18" height="12" data-path="images/augment-icon-smile.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=280&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a8dbbf105bd40aba81b68a8d4a201a9b 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=560&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ceadb84e919f3b37196015245795a07b 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=840&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1429216a05326906607010bb8f5b6c5f 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1100&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2baf591f8e787b1fe0d597f94d07fa9a 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1650&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2d12c3d3d9908f5059b1ad5cf5403402 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=2500&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=903c35569e24b232be24f720a097f896 2500w" data-optimize="true" data-opv="2" /> in the status bar.
  </Step>

  <Step title="Sync your workspace">
    If this is your first time using Augment, or you are working on a new workspace, you will see the <Command text="Sync modal" /> in the Augment panel. Click the <Command text="Sync" /> button in the Augment panel to enable Augment's rich codebase awareness. See [Syncing your workspace](/setup-augment/workspace-indexing) to customize syncing behavior and learn more.
  </Step>
</Steps>

## Sign out

<Steps>
  <Step title="Show the Augment command menu">
    Press <Keyboard shortcut="Cmd/Ctrl Shift A" /> to show the Augment command menu.
  </Step>

  <Step title="Click Sign Out">Click <Command text="Sign Out" /> from the bottom of the commands menu.</Step>

  <Step title="You are now signed out of Augment">
    You will see the status bar icon change to orange and you will be signed out of Augment in all of your active workspaces.
  </Step>
</Steps>


# Keyboard Shortcuts for Visual Studio Code
Source: https://docs.augmentcode.com/setup-augment/vscode-keyboard-shortcuts

Augment integrates with your IDE to provide keyboard shortcuts for common actions. Use these shortcuts to quickly accept suggestions, write code, and navigate your codebase.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## About keyboard shortcuts

Augment is deeply integrated into your IDE and utilizes many of the standard keyboard shortcuts you are already familiar with. These shortcuts allow you to quickly accept suggestions, write code, and navigate your codebase. We also suggest updating a few keyboard shortcuts to make working with code suggestions even easier.

<Tabs>
  <Tab title="MacOS">
    To update keyboard shortcuts, use one of the following:

    | Method          | Action                                                                                                  |   |
    | :-------------- | :------------------------------------------------------------------------------------------------------ | - |
    | Keyboard        | <Keyboard shortcut="Cmd K" /> then <Keyboard shortcut="Cmd S" />                                        |   |
    | Menu bar        | <Command text="Code > Settings... > Keyboard Shortcuts" />                                              |   |
    | Command palette | <Keyboard shortcut="Cmd Shift P" /> then search <Command text="Preferences: Open Keyboard Shortcuts" /> |   |

    ## General

    | Action                | Recommended shortcut                |
    | :-------------------- | :---------------------------------- |
    | Open Augment panel    | <Keyboard shortcut="Cmd L" />       |
    | Show Augment commands | <Keyboard shortcut="Cmd Shift A" /> |

    ## Chat

    | Action                   | Default shortcut              |
    | :----------------------- | :---------------------------- |
    | Focus or open Chat panel | <Keyboard shortcut="Cmd L" /> |

    ## Next Edit

    | Action            | Default shortcut                    |
    | :---------------- | :---------------------------------- |
    | Go to next        | <Keyboard shortcut="Cmd ;" />       |
    | Go to previous    | <Keyboard shortcut="Cmd Shift ;" /> |
    | Accept suggestion | <Keyboard shortcut="Enter" />       |
    | Reject suggestion | <Keyboard shortcut="Backspace" />   |

    ## Instructions

    | Action            | Default shortcut               |
    | :---------------- | :----------------------------- |
    | Start instruction | <Keyboard shortcut="Cmd I" />  |
    | Accept            | <Keyboard shortcut="Return" /> |
    | Reject            | <Keyboard shortcut="Esc" />    |

    ## Completions

    | Action                         | Default keyboard shortcut              |
    | :----------------------------- | :------------------------------------- |
    | Accept inline suggestion       | <Keyboard shortcut="Tab" />            |
    | Accept next word of suggestion | <Keyboard shortcut="Cmd →" />          |
    | Accept next line of suggestion | None (see below)                       |
    | Reject suggestion              | <Keyboard shortcut="Esc" />            |
    | Ignore suggestion              | Continue typing through the suggestion |
    | Toggle automatic completions   | <Keyboard shortcut="Cmd Option A" />   |

    **Recommended shortcuts**

    We recommend updating your keybindings to include the following shortcuts to
    make working with code suggestions even easier. These changes update the
    default behavior of Visual Studio Code.

    | Action                         | Recommended shortcut               |
    | :----------------------------- | :--------------------------------- |
    | Accept next line of suggestion | <Keyboard shortcut="Cmd Ctrl →" /> |
  </Tab>

  <Tab title="Windows/Linux">
    To update keyboard shortcuts, use one of the following:

    | Method          | Action                                                                                                   |
    | :-------------- | :------------------------------------------------------------------------------------------------------- |
    | Keyboard        | <Keyboard shortcut="Ctrl K" /> then <Keyboard shortcut="Ctrl S" />                                       |
    | Menu bar        | <Command text="File > Settings... > Keyboard Shortcuts" />                                               |
    | Command palette | <Keyboard shortcut="Ctrl Shift P" /> then search <Command text="Preferences: Open Keyboard Shortcuts" /> |

    ## General

    | Action                | Recommended shortcut                 |
    | :-------------------- | :----------------------------------- |
    | Open Augment panel    | <Keyboard shortcut="Ctrl L" />       |
    | Show Augment commands | <Keyboard shortcut="Ctrl Shift A" /> |

    ## Chat

    | Action                   | Default shortcut               |
    | :----------------------- | :----------------------------- |
    | Focus or open Chat panel | <Keyboard shortcut="Ctrl L" /> |

    ## Next Edit

    | Action            | Default shortcut                     |
    | :---------------- | :----------------------------------- |
    | Go to next        | <Keyboard shortcut="Ctrl ;" />       |
    | Go to previous    | <Keyboard shortcut="Ctrl Shift ;" /> |
    | Accept suggestion | <Keyboard shortcut="Enter" />        |
    | Reject suggestion | <Keyboard shortcut="Backspace" />    |

    ## Instructions

    | Action            | Default shortcut               |
    | :---------------- | :----------------------------- |
    | Start instruction | <Keyboard shortcut="Ctrl I" /> |
    | Accept            | <Keyboard shortcut="Return" /> |
    | Reject            | <Keyboard shortcut="Esc" />    |

    ## Completions

    | Action                         | Default keyboard shortcut              |
    | :----------------------------- | :------------------------------------- |
    | Accept inline suggestion       | <Keyboard shortcut="Tab" />            |
    | Accept next word of suggestion | <Keyboard shortcut="Ctrl →" />         |
    | Accept next line of suggestion | None (see below)                       |
    | Reject suggestion              | <Keyboard shortcut="Esc" />            |
    | Ignore suggestion              | Continue typing through the suggestion |
    | Toggle automatic completions   | <Keyboard shortcut="Ctrl Alt A" />     |

    **Recommended shortcuts**

    We recommend updating your keybindings to include the following shortcuts to
    make working with code suggestions even easier. These changes update default
    behavior of Visual Studio Code.

    | Action                         | Recommended shortcut               |
    | :----------------------------- | :--------------------------------- |
    | Accept next line of suggestion | <Keyboard shortcut="Ctrl Alt →" /> |
  </Tab>
</Tabs>


# Add context to your workspace
Source: https://docs.augmentcode.com/setup-augment/workspace-context-vscode

You can add additional context to your workspace–such as additional repositories and folders–to give Augment a full view of your system.

export const Availability = ({tags}) => {
  const tagTypes = {
    invite: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    beta: {
      styles: "border border-zinc-500/20 bg-zinc-50/50 dark:border-zinc-500/30 dark:bg-zinc-500/10 text-zinc-900 dark:text-zinc-200"
    },
    vscode: {
      styles: "border border-sky-500/20 bg-sky-50/50 dark:border-sky-500/30 dark:bg-sky-500/10 text-sky-900 dark:text-sky-200"
    },
    jetbrains: {
      styles: "border border-amber-500/20 bg-amber-50/50 dark:border-amber-500/30 dark:bg-amber-500/10 text-amber-900 dark:text-amber-200"
    },
    vim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    neovim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    default: {
      styles: "bg-gray-200"
    }
  };
  return <div className="flex items-center space-x-2 border-b pb-4 border-gray-200 dark:border-white/10">
      <span className="text-sm font-medium">Availability</span>
      {tags.map(tag => {
    const tagType = tagTypes[tag] || tagTypes.default;
    return <div key={tag} className={`px-2 py-0.5 rounded-md text-xs font-medium ${tagType.styles}`}>
            {tag}
          </div>;
  })}
    </div>;
};

export const Command = ({text}) => <span className="font-bold">{text}</span>;

<Availability tags={["vscode",]} />

## About Workspace Context

Augment is powered by its deep understanding of your code. Sometimes important parts of your system exist outside of the current workspace you have open in your IDE. For example, you may have seperate frontend and backend repositories or have many services across multiple repositories. Adding additional context to your workspace will improve the code suggestions and chat responses from Augment.

## View Workspace Context

To view your Workspace Context, click the folder icon <Icon icon="folder-open" iconType="light" /> in the top right corner of the Augment sidebar panel.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/workspace-context.png?maxW=1156&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=f233967febe40b6f0b72e4a7f308da5b" alt="Workspace Context" className="rounded-xl" width="1156" height="1009" data-path="images/workspace-context.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/workspace-context.png?w=280&maxW=1156&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b94f7de1698c3e371f19c6d6d7aacc01 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/workspace-context.png?w=560&maxW=1156&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4fa56865ec4a91908d915ddc532c71c9 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/workspace-context.png?w=840&maxW=1156&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=521138bd9446649f4f03fd7fb50860a9 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/workspace-context.png?w=1100&maxW=1156&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=15847ba0a7b69f5f1a4e210df20623f6 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/workspace-context.png?w=1650&maxW=1156&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=7df0be621e2a5dc9c9b867e1f9e9e7c8 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/workspace-context.png?w=2500&maxW=1156&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=bd649861ae88b55e7382627153c9d130 2500w" data-optimize="true" data-opv="2" />

## Add context to your workspace

To add context to your workspace, click <Command text="+ Add more..." /> at the bottom of the Source Folders section of the context manager. From the file browser select the folders you want to add to your workspace context and click <Command text="Add Source Folder" />.

## View sync status

When viewing Workspace Context, each file and folder will have an icon that indicates whether its sync status. The following icons indicate the sync status of each file in your workspace:

|                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 Indicator                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | Status                                  |
| :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------- |
|                                         <img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-included.svg?maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=8c4d087c628f84070b07bbca95f17b46" className="inline h-4 p-0 m-0" width="12" height="12" data-path="images/wsc-included.svg" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-included.svg?w=280&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=5a403a465572fd3fcfee467185b32d77 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-included.svg?w=560&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=aec6a233f63147eb5902a321b6761b83 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-included.svg?w=840&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=bad5cd53ad3a911a627e3f8a6d37bc1d 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-included.svg?w=1100&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=16291d432273255ad84fb7013d372274 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-included.svg?w=1650&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a1e949ed9ffa71ad1dd2ae1bf84bf3aa 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-included.svg?w=2500&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=11463a2dc2c025cf8d3412be17e7e405 2500w" data-optimize="true" data-opv="2" />                                         | Synced, or sync in progress             |
|                                         <img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-excluded.svg?maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=2394351bf1152469e1642152f85d4344" className="inline h-4 p-0 m-0" width="12" height="12" data-path="images/wsc-excluded.svg" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-excluded.svg?w=280&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=81eb2cfb7ef732d609be5a381acabcc9 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-excluded.svg?w=560&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b31ad12dfc94e8034a7098c88b3d22c0 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-excluded.svg?w=840&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=556ce47fb8d0dbeb97d279d40cbf1172 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-excluded.svg?w=1100&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=26de3e16cf8cf2fcf2a4ce7429a042dd 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-excluded.svg?w=1650&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=f036b7079bfa49280f627f27fe377f1f 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-excluded.svg?w=2500&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=eece8dd3cf47eb188f678dab747c1c63 2500w" data-optimize="true" data-opv="2" />                                         | Not synced                              |
| <img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-partially-included.svg?maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b08d72e7bdae4183addb6581a3d16399" className="inline h-4 p-0 m-0" width="12" height="12" data-path="images/wsc-partially-included.svg" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-partially-included.svg?w=280&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=0384df409ee8f7b127ca46353bd6d5f8 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-partially-included.svg?w=560&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=560cffdf2da026da01559eb74fe87498 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-partially-included.svg?w=840&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=489df52cbb7f656c84a12894cbb5c9a0 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-partially-included.svg?w=1100&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c69d6c07fa23288a6915e5ef32f1cf5c 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-partially-included.svg?w=1650&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=67aaca1cd479bb328ebf78290f3d0103 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/wsc-partially-included.svg?w=2500&maxW=12&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=525debd9503b76c21e5f6cf674818d79 2500w" data-optimize="true" data-opv="2" /> | Some files within the folder are synced |


# Index your workspace
Source: https://docs.augmentcode.com/setup-augment/workspace-indexing

When your workspace is indexed, Augment can provide tailored code suggestions and answers based on your unique codebase, best practices, coding patterns, and preferences. You can always control what files are indexed.

## About indexing your workspace

When you open a workspace with Augment enabled, your codebase will be automatically uploaded to Augment's secure cloud. You can control what files get indexed using `.gitignore` and `.augmentignore` files. Indexing usually takes less than a minute but can take longer depending on the size of your codebase. In Visual Studio Code, you can use Workspace Context to [view what files are indexed](/setup-augment/workspace-context-vscode#view-index-status-in-visual-studio-code) and [add additional context](/setup-augment/workspace-context-vscode#add-context-to-your-workspace).

## Security and privacy

Augment stores your code securely and privately to enable our powerful context engine. We ensure code privacy through a proof-of-possession API and maintain strict internal data minimization principles. [Read more about our security](https://www.augmentcode.com/security).

## What gets indexed

Augment will index all the files in your workspace, except for the files that match patterns in your `.gitignore` file and the `.augmentignore` file. You can [view what files are indexed](/setup-augment/workspace-context-vscode#view-sync-status-in-visual-studio-code) in Workspace Context.

## Ignoring files with .augmentignore

The `.augmentignore` file is a list of file patterns that Augment will ignore when indexing your workspace. Create an `.augmentignore` file in the root of your workspace. You can use any glob pattern that is supported by the [gitignore](https://git-scm.com/docs/gitignore) file.

## Including files that are .gitignored

If you have a file or directory in your `.gitignore` that you want to indexed, you can add it to your `.augmentignore` file using the `!` prefix.

For example, you may want your `node_modules` indexed to provide Augment with context about the dependencies in their project, but it is typically included in their `.gitignore`. Add `!node_modules` to your `.augmentignore` file.

<CodeGroup>
  ```bash .augmentignore
  # Include .gitignore excluded files with ! prefix
  !node_modules

  # Exclude other files with .gitignore syntax
  data/test.json
  ```

  ```bash .gitignore
  # Exclude dependencies
  node_modules

  # Exclude secrets
  .env

  # Exclude build artifacts
  out
  build
  ```
</CodeGroup>


# Feedback
Source: https://docs.augmentcode.com/troubleshooting/feedback

We love feedback, and want to hear from you. We want to make the best AI-powered code assistant so you can get more done.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

Feedback helps us improve, and we encourage you to share your feedback on every aspect of using Augment—from suggestion and chat response quality, to user experience nusances, and even how we can improve getting your feedback.

### Reporting a bug

To report a bug, please [contact support](https://support.augmentcode.com/). Include as much detail to reproduce the problem as possible; screenshots and videos are very helpful.

### Feedback on completions

We are always balancing the needs for speed and accuracy. We want to know when you get a poor suggestion, hallucination, or a completion that actually doesn't work. The History panel has a log of all of your completions; we encourage you to use it to send us feedback on the completions you've received.

<Note>
  Providing feedback directly in your IDE through the History panel is currently
  only available in Visual Studio Code.
</Note>

<Steps>
  <Step title="Open the History panel">
    Open the History panel by pressing <Keyboard shortcut="Cmd/Ctrl Shift P" />
    and then searching for `Augment: Show History` in the command menu.
  </Step>

  <Step title="Find the completion you want to report">
    Recent completions are listed in reverse chronological order. Locate the
    completion you want to report and add complete the feedback form.
  </Step>

  <Step title="Submit your feedback">
    After completing the form, click either the red button for bad completions
    or the green button for good completions.
  </Step>
</Steps>

### Feedback on chat

After each Chat interaction, you have the opportunity to provide feedback on the quality of the response. At the bottom of the response click either the thumbs up <Icon icon="thumbs-up" iconType="light" /> or thumbs down <Icon icon="thumbs-down" iconType="light" /> icon. Add additional information in the feedback field, and click `Send Feedback`.


# Jetbrains rendering issues
Source: https://docs.augmentcode.com/troubleshooting/jetbrains-rendering-issues

Fix issue where the Augment panel is white or blank in JetBrains IDEs.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About rendering issues in JetBrains IDEs

Some users on on newer versions of JetBrains IDEs have reported that the Augment panel is white or blank. This issue can be resolved by disabling out-of-process rendering in your JetBrains IDE.

### Disable out-of-process rendering

<Steps>
  <Step title="Open the Custom Properties editor">
    From the menu bar, go to <Command text="Help > Edit Custom Properties..." />. If the `idea.properties` file doesn't exist yet, you'll be prompted to create it.
  </Step>

  <Step title="Add the out-of-process rendering property">
    Add the following line to the properties file:

    ```
    ide.browser.jcef.out-of-process.enabled=false
    ```
  </Step>

  <Step title="Save and restart your IDE">
    Save the file and restart your JetBrains IDE for the changes to take effect.
  </Step>
</Steps>

After restarting, the Augment panel should render more consistently.


# Jetbrains panel steals focus
Source: https://docs.augmentcode.com/troubleshooting/jetbrains-stealing-focus

Fix issue where the Augment panel takes focus while typing in JetBrains IDEs.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About focus issues in JetBrains IDEs

Some users on Linux systems have reported that the Augment Chat window steals focus from the editor while typing. This can interrupt your workflow and make it difficult to use the IDE effectively. This issue can be resolved by enabling off-screen rendering in your JetBrains IDE.

### Enable off-screen rendering

<Steps>
  <Step title="Open the Custom Properties editor">
    From the menu bar, go to <Command text="Help > Edit Custom Properties..." />. If the `idea.properties` file doesn't exist yet, you'll be prompted to create it.
  </Step>

  <Step title="Add the off-screen rendering property">
    Add the following line to the properties file:

    ```
    augment.off.screen.rendering=true
    ```
  </Step>

  <Step title="Save and restart your IDE">
    Save the file and restart your JetBrains IDE for the changes to take effect.
  </Step>
</Steps>

After restarting, the Augment panel should no longer steal focus from the editor while you're typing.


# Request IDs
Source: https://docs.augmentcode.com/troubleshooting/request-id

Request IDs are generated with every code suggestion and chat interaction. Our team may ask you to provide the request ID when you report a bug or issue.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## Finding a Request ID for Chat

<Steps>
  <Step title="Open the Chat panel">
    Open the Chat panel by clicking the Augment icon{" "}

    <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4eb384ca1634865b22f3c425c0e6027a" className="inline h-4 p-0 m-0" width="676" height="592" data-path="images/augment-icon-chat.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=280&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d683c31717e6be4da8863bde3cf419da 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=560&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5b89065b94498b88f97aadedb61dcaad 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=840&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=81448b7ddd95b2212098280d7129474d 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=1100&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3733a3a239dadbbb94c6600613e1a2e3 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=1650&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e9e7d6e2faecca5aabadd73d008d9a85 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=2500&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=72f66dab3541e6e71e3141a52c755331 2500w" data-optimize="true" data-opv="2" />

    {" "}

    in the action bar on the left side of your editor.
  </Step>

  <Step title="Open the chat thread">
    If the chat reply you are interested is in a previous chat thread, find the
    chat thread by clicking the <Icon icon="chevron-right" /> at the top of the
    chat panel and clicking the relevant chat thread.
  </Step>

  <Step title="Find the request ID">
    Find the reply in question and click the <Icon icon="link-simple" /> icon
    above the reply to copy the request ID to your clipboard.
  </Step>
</Steps>

## Finding a Request ID for Completions

<Steps>
  <Step title="Open the History panel">
    Open the History panel by pressing <Keyboard shortcut="Cmd/Ctrl Shift P" />
    and then searching for `Augment: Show History` in the command menu.
  </Step>

  <Step title="Find the request ID">
    Recent requests are listed in reverse chronological order. Locate the
    request you are interested in and copy the request ID by clicking on the
    request ID, for example:
    <br /> `-- Request ID: 7f67c0dd-4c80-4167-9383-8013b18836cb`
  </Step>
</Steps>


# Using Agent
Source: https://docs.augmentcode.com/using-augment/agent

Use Agent to complete simple and complex tasks across your workflow–implementing a feature, upgrade a dependency, or writing a pull request.

export const type_0 = "changes"

export const AtIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M480.39-96q-79.52 0-149.45-30Q261-156 208.5-208.5T126-330.96q-30-69.96-30-149.5t30-149.04q30-69.5 82.5-122T330.96-834q69.96-30 149.5-30t149.04 30q69.5 30 122 82.5t82.5 122Q864-560 864-480v60q0 54.85-38.5 93.42Q787-288 732-288q-34 0-62.5-17t-48.66-45Q593-321 556.5-304.5T480-288q-79.68 0-135.84-56.23-56.16-56.22-56.16-136Q288-560 344.23-616q56.22-56 136-56Q560-672 616-615.84q56 56.16 56 135.84v60q0 25.16 17.5 42.58Q707-360 732-360t42.5-17.42Q792-394.84 792-420v-60q0-130-91-221t-221-91q-130 0-221 91t-91 221q0 130 91 221t221 91h192v72H480.39ZM480-360q50 0 85-35t35-85q0-50-35-85t-85-35q-50 0-85 35t-35 85q0 50 35 85t85 35Z" />
    </svg>
  </div>;

## About Agent

Augment Agent is a powerful tool that can help you complete software development tasks end-to-end. From quick edits to complete feature implementation, Agent breaks down your requests into a functional plan and implements each step all while keeping you informed about what actions and changes are happening. Powered by Augment's Context Engine and powerful LLM architecture, Agent can write, document, and test like an experienced member of your team.

## Accessing Agent

To access Agent, simply open the Augment panel and select one of the Agent modes from the drop down in the input box.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector.png?maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8b2375d2203e891b57da96e97fa496e8" alt="Augment Agent" className="rounded-xl" width="1235" height="434" data-path="images/agent-selector.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector.png?w=280&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c9615aa13c225ebd35dca8f9263b66f0 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector.png?w=560&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7f411060a6ecd8c79c5c2d9bfa72c419 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector.png?w=840&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7e819bf7306ee64b59e52e36635e09b9 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector.png?w=1100&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1fa312460d344076400e95f71c5b6e0c 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector.png?w=1650&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6b43c52a0e6aa30c6ad0b2b24f7c6ef9 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-selector.png?w=2500&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c5c1e7e2ced598bfa3a9bb53c33a1f70 2500w" data-optimize="true" data-opv="2" />

### Choosing a model

Use the model dropdown in the Augment panel to switch between Claude Sonnet 4 and GPT-5. Your selection applies only to Agent for the current workspace and can be changed at any time. See [Available Models](/models/available-models) for details.

## Using Agent

To use Agent, simply type your request into the input box using natural language and click the submit button. You will see the default context including current workspace, current file, and Agent memories. You can add additional context by clicking <AtIcon />and selecting files or folder, or add an image as context by clicking the paperclip. Agent can create, edit, or delete code across your workspace and can use tools like the terminal and external integrations through MCP to complete your request.

### Enhancing your prompt

You can improve the quality of your {type_0} by starting with a well crafted prompt. You can start with a quick or incomplete prompt and use the prompt enhancer to add relevant references, structure, and conventions from your codebase to improve the prompt before it is sent.

1. Write your prompt in the prompt input box
2. Click the Enhance Prompt ✨ button
3. Review and edit the enhanced prompt
4. Submit your prompt

### Reviewing changes

You can review every change Agent makes by clicking on the action to expand the view. Review diffs for file changes, see complete terminal commands and output, and the results of external integration calls.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=992e233d6c319b35fda89cce50ffd480" alt="Augment Agent" className="rounded-xl" width="1235" height="543" data-path="images/agent-edit.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=280&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=de3af323730e413ae5aa068f45f96d69 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=560&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a21dda07e1990ee1ce08d78cfa4d927d 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=840&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1d204328804871ef7aeffb148b23674e 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=1100&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6e1f4b4037e539116b27598a96dc992c 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=1650&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=10dd9f8c50efdf339e6a430f7378ae68 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=2500&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c2942a51e3c30b108c4a52d572083179 2500w" data-optimize="true" data-opv="2" />

### Checkpoints

Checkpoints are automatically saved snapshots of your workspace as Agent implements the plan allowing you to easily revert back to a previous step. This enables Agent to continue working while you review code changes and commands results. To revert to a previous checkpoint, click the reverse arrow icon to restore your code.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint.png?maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3c46f63efee1ffe97e83818648b20c67" alt="Augment Agent" className="rounded-xl" width="1235" height="286" data-path="images/agent-checkpoint.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint.png?w=280&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=84a72a6312e7235d4b67871b499af3af 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint.png?w=560&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f47b45714cefff0b7c64d3b2605af880 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint.png?w=840&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c54e6a841845f952d783c6e888fb97ad 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint.png?w=1100&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=336ded34d2029bbbc11906ab20fe793e 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint.png?w=1650&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1e15e9a7bc75c8e57e2b18abc01ae97c 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-checkpoint.png?w=2500&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=66c526a4700be580110ed773de8406dc 2500w" data-optimize="true" data-opv="2" />

### Agent memories

Memories help the Agent remember important details about your workspace and your preferences for working in it. Memories are stored locally and are applied to all Agent requests. Memories can be added automatically by Agent, by clicking the remember button under a message, asking Agent to remember something, or by editing the Memories files directly.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-memories.png?maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8c39ea001893af845cdc8eaa528b9de8" alt="Stopping the agent" className="rounded-xl" width="1235" height="377" data-path="images/agent-memories.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-memories.png?w=280&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=40d88507bfb4a22115d84c35b21d0e04 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-memories.png?w=560&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d3418a821e74ed4521fde10bbbc776f4 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-memories.png?w=840&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8c8b8f347c4f4ae308f0e4a98833e40a 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-memories.png?w=1100&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=45f28b4fbf305a6462bae2de851571b8 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-memories.png?w=1650&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8edba2217389a098ef414b1f61869d64 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-memories.png?w=2500&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2f702f4404796860cb6d505a842182d6 2500w" data-optimize="true" data-opv="2" />

### Agent vs Agent Auto

By default, Agent will pause work when it needs to execute a terminal command or access external integrations. After reviewing the suggested action, click the blue play button to have Agent execute the command and continue working. You tell Agent to skip a specific action by clicking on the three dots and then Skip.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1b04d9b700359cbd93a793a05bfee16b" alt="Augment Agent" className="rounded-xl" width="1212" height="373" data-path="images/agent-approval.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=280&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=211526cd1fe7cf7dcf5cfb52c89f2b60 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=560&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b246ebb0bf5adb7fa8edd1b5ff97302b 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=840&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a9d430ebf10aed36b2509a24f9102424 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=1100&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=662e2e65e9a3aac77ca8fa84119e8991 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=1650&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=57216409281129a06b8195f0ab4a5098 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-approval.png?w=2500&maxW=1212&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b0a9fb0adb44ea4d1966cdfa9cf01d75 2500w" data-optimize="true" data-opv="2" />

In Agent Auto, Agent will act more independently. It will edit files, execute terminal commands, and access tools like MCP servers automatically.

### Stop or guide the Agent

You can interrupt the Agent at any time by clicking Stop. This will pause the action to allow you to correct something you see the agent doing incorrectly. While Agent is working, you can also prompt the Agent to try a different approach which will automatically stop the agent and prompt it to correct its course.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8adf60259160c542d805bcd6dfbd71d7" alt="Stopping the agent" className="rounded-xl" width="1235" height="551" data-path="images/agent-stop.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=280&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9d29956804de18551c3b9cae1543fd00 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=560&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=13018a76b55cb0771d9eef71acf4f0a3 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=840&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f252fd53effffea19cda1bd38fe03dfa 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=1100&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=06e3604c8289c4bf9c4a305452258cbd 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=1650&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1fcb7b60297659b355ffe773204728fd 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-stop.png?w=2500&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=14d6439fe81383ee2a908944923082a4 2500w" data-optimize="true" data-opv="2" />

### Quick Ask Mode

Quick Ask Mode is a toggle button in the agent chat interface that restricts the AI to read-only tools only. When activated, it adds a visual badge to the message and focuses the AI on information gathering without making any changes to your codebase.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=532f998cb0492e3645a9da69d758222a" alt="Quick Ask Mode toggle and usage" className="rounded-xl" width="800" height="450" data-path="images/ask-mode.gif" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=280&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0f926dcab335ce982ad465adbd847b68 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=560&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e09601fed4a527a3f6f22bd47ed52593 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=840&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a50f1f942f70e6ead193515fa2537ae7 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=1100&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3cbc23ea085ccf08f42c91bd8b41473a 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=1650&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b1f8d6f164d2244871f933f4c40f0c3a 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/ask-mode.gif?w=2500&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=64749cbed3fc09bb51b82fbc99d02bff 2500w" data-optimize="true" data-opv="2" />

### Comparison to Chat

Agent takes Chat to the next level by allowing Augment to do things for you-that is create and make modifications directly to your codebase. Chat can explain code, create plans, and suggest changes which you can smartly apply one-by-one, but Agent takes it a step further by automatically implementing the entire plan and all code changes for you.

| What are you trying to do?                       | Chat | Agent |
| :----------------------------------------------- | :--: | :---: |
| Ask questions about your code                    |  ☑️  |   ✅   |
| Get advice on how to refactor code               |  ☑️  |   ✅   |
| Add new features to selected lines of code       |  ☑️  |   ✅   |
| Add new feature spanning multiple files          |      |   ✅   |
| Document new features                            |      |   ✅   |
| Queue up tests for you in the terminal           |      |   ✅   |
| Open Linear tickets or start a pull request      |      |   ✅   |
| Start a new branch in GitHub from recent commits |      |   ✅   |
| Automatically perform tasks on your behalf       |      |   ✅   |

### Use cases

Use Agent to handle various aspects of your software development workflow, from simple configuration changes to complex feature implementations. Agent supports your daily engineering tasks like:

* **Make quick edits** - Create a pull request to adjust configuration values like feature flags from FALSE to TRUE
* **Perform refactoring** - Move functions between files while maintaining coding conventions and ensuring bug-free operation
* **Start a first draft for new features** - Start a pull request (PR) with implementing entirely new functionality straight from a GitHub Issue or Linear Ticket
* **Branch from GitHub** - Open a PR from GitHub based on recent commits that creates a new branch
* **Query Supabase tables directly** - Ask Agent to view the contents of a table
* **Start tickets in Linear or Jira** - Open tickets and ask Agent to suggest a plan to address the ticket
* **Add Pull Request descriptions** - Merge your PR into a branch then tell the agent to explain what the changes are and why they were made
* **Create test coverage** - Generate unit tests for your newly developed features
* **Generate documentation** - Produce comprehensive documentation for your libraries and features
* **Start a README** - Write a README for a new feature or updated function that you just wrote
* **Track development progress** - Review and summarize your recent Git commits for better visibility with the GitHub integration

## Next steps

* [Configure Agent Integrations](/setup-augment/agent-integrations)
* [Configure other tools with MCP](/setup-augment/mcp)


# Using Chat
Source: https://docs.augmentcode.com/using-augment/chat

Use Chat to explore your codebase, quickly get up to speed on unfamiliar code, and get help working through a technical problem.

export const type_0 = "chats"

export const DeleteIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M280-120q-33 0-56.5-23.5T200-200v-520h-40v-80h200v-40h240v40h200v80h-40v520q0 33-23.5 56.5T680-120H280Zm400-600H280v520h400v-520ZM360-280h80v-360h-80v360Zm160 0h80v-360h-80v360ZM280-720v520-520Z" />
    </svg>
  </div>;

export const ChevronRightIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M504-480 320-664l56-56 240 240-240 240-56-56 184-184Z" />
    </svg>
  </div>;

export const NewChatIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M120-160v-600q0-33 23.5-56.5T200-840h480q33 0 56.5 23.5T760-760v203q-10-2-20-2.5t-20-.5q-10 0-20 .5t-20 2.5v-203H200v400h283q-2 10-2.5 20t-.5 20q0 10 .5 20t2.5 20H240L120-160Zm160-440h320v-80H280v80Zm0 160h200v-80H280v80Zm400 280v-120H560v-80h120v-120h80v120h120v80H760v120h-80ZM200-360v-400 400Z" />
    </svg>
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About Chat

Chat is a new way to work with your codebase using natural language. Chat will automatically use the current workspace as context and you can [provide focus](/using-augment/chat-context) for Augment by selecting specific code blocks, files, folders, or external documentation. Details from your current chat, including the additional context, are used to provide more relevant code suggestions as well.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9879d970e519862e4ab098bbce847bd8" alt="Augment Chat" className="rounded-xl" width="1120" height="1209" data-path="images/chat-explain.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=280&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d0ba44e92fe571fd6cfeb40bd6dad254 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=560&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=491571511ea5171f894d977a83e03f8d 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=840&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=bdae0be74d6fd0037486829dad5b898f 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=1100&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8bd9d2dd93ecb67abbc1b74684a86561 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=1650&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=141c7d3a71afd54cc2e3ca910e5a1d6d 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-explain.png?w=2500&maxW=1120&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=82d357d200d56405236a3c353095847c 2500w" data-optimize="true" data-opv="2" />

## Accessing Chat

Access the Chat sidebar by clicking the Augment icon <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4eb384ca1634865b22f3c425c0e6027a" className="inline h-4 p-0 m-0" width="676" height="592" data-path="images/augment-icon-chat.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=280&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d683c31717e6be4da8863bde3cf419da 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=560&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5b89065b94498b88f97aadedb61dcaad 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=840&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=81448b7ddd95b2212098280d7129474d 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=1100&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3733a3a239dadbbb94c6600613e1a2e3 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=1650&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e9e7d6e2faecca5aabadd73d008d9a85 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-chat.png?w=2500&maxW=676&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=72f66dab3541e6e71e3141a52c755331 2500w" data-optimize="true" data-opv="2" /> in the sidebar or the status bar. You can also open Chat by using one of the keyboard shortcuts below.

**Keyboard Shortcuts**

| Platform      | Shortcut                       |
| :------------ | :----------------------------- |
| MacOS         | <Keyboard shortcut="Cmd L" />  |
| Windows/Linux | <Keyboard shortcut="Ctrl L" /> |

## Using Chat

To use Chat, simply type your question or command into the input field at the bottom of the Chat panel. You will see the currently included context which includes the workspace and current file by default. Use Chat to explain your code, investigate a bug, or use a new library. See [Example Prompts for Chat](/using-augment/chat-prompts) for more ideas on using Chat.

### Conversations about code

To get the best possible results, you can go beyond asking simple questions or commands, and instead have a back and forth conversation with Chat about your code. For example, you can ask Chat to explain a specific function and then ask follow-up questions about possible refactoring options. Chat can act as a pair programmer, helping you work through a technical problem or understand unfamiliar code.

### Enhancing your prompt

You can improve the quality of your {type_0} by starting with a well crafted prompt. You can start with a quick or incomplete prompt and use the prompt enhancer to add relevant references, structure, and conventions from your codebase to improve the prompt before it is sent.

1. Write your prompt in the prompt input box
2. Click the Enhance Prompt ✨ button
3. Review and edit the enhanced prompt
4. Submit your prompt

### Starting a new chat

You should start a new Chat when you want to change the topic of the conversation since the current conversation is used as part of the context for your next question. To start a new chat, open the Augment panel and click the new chat icon <NewChatIcon /> at the top-right of the Chat panel.

### Previous chats

You can continue a chat by clicking the chevron icon<ChevronRightIcon />at the top-left of the Chat panel. Your previous chats will be listed in reverse chronological order, and you can continue your conversation where you left off.

### Deleting a chat

You can delete a previous chat by clicking the chevron icon<ChevronRightIcon />at the top-left of the Chat panel to show the list of previous chats. Click the delete icon <DeleteIcon /> next to the chat you want to delete. You will be asked to confirm that you want to delete the chat.


# Using Actions in Chat
Source: https://docs.augmentcode.com/using-augment/chat-actions

Actions let you take common actions on code blocks without leaving Chat. Explain, improve, or find everything you need to know about your codebase.

export const ArrowUpIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M444-192v-438L243-429l-51-51 288-288 288 288-51 51-201-201v438h-72Z" />
    </svg>
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ee847c45ac860ebd63010152269cf1fa" alt="Augment Chat Actions" className="rounded-xl" width="1233" height="630" data-path="images/chat-actions.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=280&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=11a0ee3cd4160ea86ad2e874cee1ae30 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=560&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5309c23856e22b1127b81890fdcafe23 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=840&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e8c790ce5d9b150637667dcaa640a2a9 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=1100&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=038ef29bb227d0446e760179fd21bc13 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=1650&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ee76b9ecd69421411e98e013bce0efa5 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-actions.png?w=2500&maxW=1233&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=26f30c2a55be51fde45b2fd8a1573c23 2500w" data-optimize="true" data-opv="2" />

## Using actions in Chat

To use a quick action, you an use a <Keyboard shortcut="/" /> command or click the up arrow icon<ArrowUpIcon />to show the available actions. For explain, fix, and test actions, first highlight the code in the editor and then use the command.

| Action                           | Usage                                                                    |
| :------------------------------- | :----------------------------------------------------------------------- |
| <Keyboard shortcut="/find" />    | Use natural language to find code or functionality                       |
| <Keyboard shortcut="/explain" /> | Augment will explain the hightlighted code                               |
| <Keyboard shortcut="/fix" />     | Augment will suggest improvements or find errors in the highlighted code |
| <Keyboard shortcut="/test" />    | Augment will suggest tests for the highlighted code                      |

Augment will typically include code blocks in the response to the action. See [Applying code blocks from Chat](/using-augment/chat-apply) for more details.


# Applying code blocks from Chat
Source: https://docs.augmentcode.com/using-augment/chat-apply

Use Chat to explore your codebase, quickly get up to speed on unfamiliar code, and get help working through a technical problem.

export const Availability = ({tags}) => {
  const tagTypes = {
    invite: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    beta: {
      styles: "border border-zinc-500/20 bg-zinc-50/50 dark:border-zinc-500/30 dark:bg-zinc-500/10 text-zinc-900 dark:text-zinc-200"
    },
    vscode: {
      styles: "border border-sky-500/20 bg-sky-50/50 dark:border-sky-500/30 dark:bg-sky-500/10 text-sky-900 dark:text-sky-200"
    },
    jetbrains: {
      styles: "border border-amber-500/20 bg-amber-50/50 dark:border-amber-500/30 dark:bg-amber-500/10 text-amber-900 dark:text-amber-200"
    },
    vim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    neovim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    default: {
      styles: "bg-gray-200"
    }
  };
  return <div className="flex items-center space-x-2 border-b pb-4 border-gray-200 dark:border-white/10">
      <span className="text-sm font-medium">Availability</span>
      {tags.map(tag => {
    const tagType = tagTypes[tag] || tagTypes.default;
    return <div key={tag} className={`px-2 py-0.5 rounded-md text-xs font-medium ${tagType.styles}`}>
            {tag}
          </div>;
  })}
    </div>;
};

export const MoreVertIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M479.79-192Q450-192 429-213.21t-21-51Q408-294 429.21-315t51-21Q510-336 531-314.79t21 51Q552-234 530.79-213t-51 21Zm0-216Q450-408 429-429.21t-21-51Q408-510 429.21-531t51-21Q510-552 531-530.79t21 51Q552-450 530.79-429t-51 21Zm0-216Q450-624 429-645.21t-21-51Q408-726 429.21-747t51-21Q510-768 531-746.79t21 51Q552-666 530.79-645t-51 21Z" />
    </svg>
  </div>;

export const CheckIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M389-267 195-460l51-52 143 143 325-324 51 51-376 375Z" />
    </svg>
  </div>;

export const FileNewIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M200-120q-33 0-56.5-23.5T120-200v-560q0-33 23.5-56.5T200-840h360v80H200v560h560v-360h80v360q0 33-23.5 56.5T760-120H200Zm120-160v-80h320v80H320Zm0-120v-80h320v80H320Zm0-120v-80h320v80H320Zm360-80v-80h-80v-80h80v-80h80v80h80v80h-80v80h-80Z" />
    </svg>
  </div>;

export const FileCopyIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="#5f6368" viewBox="0 -960 960 960">
      <path d="M760-200H320q-33 0-56.5-23.5T240-280v-560q0-33 23.5-56.5T320-920h280l240 240v400q0 33-23.5 
      56.5T760-200ZM560-640v-200H320v560h440v-360H560ZM160-40q-33 0-56.5-23.5T80-120v-560h80v560h440v80H
      160Zm160-800v200-200 560-560Z" />
    </svg>
  </div>;

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=774a796e289508034253da0a4eadda1d" alt="Augment Chat Apply" className="rounded-xl" width="1291" height="375" data-path="images/chat-apply.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=280&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=683274bfa6a97c689d21fa510b8c924a 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=560&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=411bc80d62b14c9ebdafd16f6bdf1816 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=840&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e3dc1ed2eb6bfe30bb082b19694f5054 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=1100&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6a996e95e03a2d613efa21fa2d18531f 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=1650&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f8bcfcfcef62342687b25edcf5ede82d 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-apply.png?w=2500&maxW=1291&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ab7acba48cc20358a9910b46f4c9ce24 2500w" data-optimize="true" data-opv="2" />

## Using code blocks from within Chat

Whenever Chat responds with code, you will have the option to add the code to your codebase. The most common option will be shown as a button and you can access the other options by clicking the overflow menu icon<MoreVertIcon />at the top-right of the code block. You can use the following options to apply the code:

* <FileCopyIcon />**Copy**
  the code from the block to your clipboard
* <FileNewIcon />**Create**
  a new file with the code from the block
* <CheckIcon />**Apply**
  the code from the block intelligently to your file


# Focusing Context in Chat
Source: https://docs.augmentcode.com/using-augment/chat-context

You can specify context from files, folders, and external documentation in your conversation to focus your chat responses.

export const AtIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M480.39-96q-79.52 0-149.45-30Q261-156 208.5-208.5T126-330.96q-30-69.96-30-149.5t30-149.04q30-69.5 82.5-122T330.96-834q69.96-30 149.5-30t149.04 30q69.5 30 122 82.5t82.5 122Q864-560 864-480v60q0 54.85-38.5 93.42Q787-288 732-288q-34 0-62.5-17t-48.66-45Q593-321 556.5-304.5T480-288q-79.68 0-135.84-56.23-56.16-56.22-56.16-136Q288-560 344.23-616q56.22-56 136-56Q560-672 616-615.84q56 56.16 56 135.84v60q0 25.16 17.5 42.58Q707-360 732-360t42.5-17.42Q792-394.84 792-420v-60q0-130-91-221t-221-91q-130 0-221 91t-91 221q0 130 91 221t221 91h192v72H480.39ZM480-360q50 0 85-35t35-85q0-50-35-85t-85-35q-50 0-85 35t-35 85q0 50 35 85t85 35Z" />
    </svg>
  </div>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About Chat Context

Augment intelligently includes context from your entire workspace based on the ongoing conversation–even if you don't have the relevant files open in your editor–but sometimes you want Augment to prioritize specific details for more relevant responses.

<video src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/chat-context.mp4?auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8209f4f16256b74970f18e1aec456f8e" loop muted controls className="rounded-xl" data-path="images/chat-context.mp4" />

### Focusing context for your conversation

You can specify context by clicking the <AtIcon /> icon at the top-left of the Chat panel or by <Command text="@-mentioning" /> in the input field. You can use fuzzy search to filter the list of context options quickly. There are a number of different types of additional context you can add to your conversation:

1. Highlighted code blocks
2. Specific files or folders within your workspace
3. 3rd party documentation, like Next.js documentation

#### Mentioning files and folders

Include specific files or folders in your context by typing `@` followed by the file or folder name. For example, `@routes.tsx` will include the `routes.tsx` file in your context. You can include multiple files or folders.

#### Mentioning 3rd party documentation

You can also mention 3rd party documentation in your context by typing `@` followed by the name of the documentation. For example, `@Next.js` will include Next.js documentation in your context. Augment provides nearly 300 documentation sets spanning across a wide range of domains such as programming languages, packages, software tools, and frameworks.


# Example Prompts for Chat
Source: https://docs.augmentcode.com/using-augment/chat-prompts

Using natural language to interact with your codebase unlocks a whole new way of working. Learn how to get the most out of Chat with the following example prompts.

export const type_0 = "chats"

## About chatting with your codebase

Augment's Chat has deep understanding about your codebase, dependencies, and best practices. You can use Chat to ask questions about your code, but it also can help you with general software engineering questions, think through technical decisions, explore new libraries, and more.

## Enhancing your prompt

You can improve the quality of your {type_0} by starting with a well crafted prompt. You can start with a quick or incomplete prompt and use the prompt enhancer to add relevant references, structure, and conventions from your codebase to improve the prompt before it is sent.

1. Write your prompt in the prompt input box
2. Click the Enhance Prompt ✨ button
3. Review and edit the enhanced prompt
4. Submit your prompt

## Example Prompts

### Explain code

* Explain this codebase to me
* How do I use the Twilio API to send a text message?
* Explain how generics work in TypeScript and give me a simple example

### Finding code

* Where are all the useEffect hooks that depend on the 'currentUser' variable?
* Find the decorators that implement retry logic across our microservices
* Find coroutines that handle database transactions without a timeout parameter

### Generate code

* Write a function to check if a string is a valid email address
* Generate a middleware function that rate-limits API requests using a sliding window algorithm
* Create a SQL query to find the top 5 customers who spent the most money last month

### Write tests

* Write integration tests for this API endpoint
* What edge cases have I not included in this test?
* Generate mock data for testing this customer order processing function

### Refactor and improve code

* This function is running slowly with large collections - how can I optimize it?
* Refactor this callback-based code to use async/await instead
* Rewrite this function in Rust

### Find and fix errors

* This endpoint sometimes returns a 500 error. Here's the error log - what's wrong?
* I'm getting 'TypeError: Cannot read property 'length' of undefined' in this component.
* Getting CORS errors when my frontend tries to fetch from the API


# Completions
Source: https://docs.augmentcode.com/using-augment/completions

Use code completions to get more done. Augment's radical context awareness means more relevant suggestions, fewer hallucinations, and less time hunting down documentation.

export const MoreVertIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" height="20px" viewBox="0 -960 960 960" width="20px" fill="#5f6368">
      <path d="M479.79-192Q450-192 429-213.21t-21-51Q408-294 429.21-315t51-21Q510-336 531-314.79t21 51Q552-234 530.79-213t-51 21Zm0-216Q450-408 429-429.21t-21-51Q408-510 429.21-531t51-21Q510-552 531-530.79t21 51Q552-450 530.79-429t-51 21Zm0-216Q450-624 429-645.21t-21-51Q408-726 429.21-747t51-21Q510-768 531-746.79t21 51Q552-666 530.79-645t-51 21Z" />
    </svg>
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About Code Completions

Augment's Code Completions integrates with your IDE's native completions system to give you autocomplete-like suggestions as you type. You can accept all of a suggestion, accept partial suggestions a word or a line at a time, or just keep typing to ignore the suggestion.

## Using Code Completions

To use code completions, simply start typing in your IDE. Augment will provide suggestions based on the context of your code. You can accept a suggestion by pressing <Keyboard shortcut="Cmd/Ctrl →" />, or ignore it by continuing to type.

For example, add the following function to a TypeScript file:

```typescript
function getUser(): Promise<User>;
```

As you type `getUser`, Augment will suggest the function signature. Press <Keyboard shortcut="Tab" /> to accept the suggestion. Augment will continue to offer suggestions until the function is complete, at which point you will have a function similar to:

```typescript
function getUser(): Promise<User> {
  return fetch("/api/user/1")
    .then((response) => response.json())
    .then((json) => {
      return json as User;
    });
}
```

### Accepting Completions

<Tabs>
  <Tab title="MacOS">
    <Tip>
      We recommend configuring a custom keybinding to accept a word or line, see
      [Keyboard shortcuts](/setup-augment/vscode-keyboard-shortcuts) for more
      details.
    </Tip>

    | Action                         | Default keyboard shortcut                       |
    | :----------------------------- | :---------------------------------------------- |
    | Accept inline suggestion       | <Keyboard shortcut="Tab" />                     |
    | Accept next word of suggestion | <Keyboard shortcut="Cmd →" />                   |
    | Accept next line of suggestion | None (see above)                                |
    | Reject suggestion              | <Keyboard shortcut="Esc" />                     |
    | Ignore suggestion              | Continue typing through the suggestion          |
    | Toggle automatic completions   | VSCode: <Keyboard shortcut="Cmd Option A" />    |
    |                                | JetBrains: <Keyboard shortcut="Cmd Option 9" /> |
  </Tab>

  <Tab title="Windows/Linux">
    <Tip>
      We recommend configuring a custom keybinding to accept a word or line, see
      [Keyboard shortcuts](/setup-augment/vscode-keyboard-shortcuts) for more
      details.
    </Tip>

    | Action                         | Default keyboard shortcut                     |
    | :----------------------------- | :-------------------------------------------- |
    | Accept inline suggestion       | <Keyboard shortcut="Tab" />                   |
    | Accept next word of suggestion | <Keyboard shortcut="Ctrl →" />                |
    | Accept next line of suggestion | None (see above)                              |
    | Reject suggestion              | <Keyboard shortcut="Esc" />                   |
    | Ignore suggestion              | Continue typing through the suggestion        |
    | Toggle automatic completions   | VSCode: <Keyboard shortcut="Ctrl Alt A" />    |
    |                                | JetBrains: <Keyboard shortcut="Ctrl Alt 9" /> |
  </Tab>
</Tabs>

### Disabling Completions

<Tabs>
  <Tab title="Visual Studio Code">
    You can disable automatic code completions by clicking the overflow menu icon<MoreVertIcon />at the top-right of the Augment panel, then selecting <Command text="Turn Automatic Completions Off" />.
  </Tab>

  <Tab title="JetBrains IDEs">
    You can disable automatic code completions by clicking the Augment icon <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0f98e2222af9b74b38faeb8c56ed09be" className="inline h-3 p-0 m-0" width="18" height="12" data-path="images/augment-icon-smile.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=280&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a8dbbf105bd40aba81b68a8d4a201a9b 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=560&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ceadb84e919f3b37196015245795a07b 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=840&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1429216a05326906607010bb8f5b6c5f 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1100&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2baf591f8e787b1fe0d597f94d07fa9a 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1650&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2d12c3d3d9908f5059b1ad5cf5403402 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=2500&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=903c35569e24b232be24f720a097f896 2500w" data-optimize="true" data-opv="2" /> in the status bar at the bottom right corner of your IDE, then selecting <Command text="Disable Completions" />.
  </Tab>
</Tabs>

### Enable Completions

<Tabs>
  <Tab title="Visual Studio Code">
    If you've temporarily disabled completions, you can re-enable them by clicking the overflow menu icon<MoreVertIcon />at the top-right of the Augment panel, then selecting <Command text="Turn Automatic Completions On" />.
  </Tab>

  <Tab title="JetBrains IDEs">
    If you've temporarily disabled completions, you can re-enable them by clicking the Augment icon <img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=0f98e2222af9b74b38faeb8c56ed09be" className="inline h-3 p-0 m-0" width="18" height="12" data-path="images/augment-icon-smile.svg" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=280&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a8dbbf105bd40aba81b68a8d4a201a9b 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=560&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=ceadb84e919f3b37196015245795a07b 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=840&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1429216a05326906607010bb8f5b6c5f 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1100&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2baf591f8e787b1fe0d597f94d07fa9a 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=1650&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2d12c3d3d9908f5059b1ad5cf5403402 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/augment-icon-smile.svg?w=2500&maxW=18&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=903c35569e24b232be24f720a097f896 2500w" data-optimize="true" data-opv="2" /> in the status bar at the bottom right corner of your IDE, then selecting <Command text="Enable Completions" />.
  </Tab>
</Tabs>


# Instructions
Source: https://docs.augmentcode.com/using-augment/instructions

Use Instructions to write or modify blocks of code using natural language. Refactor a function, write unit tests, or craft any prompt to transform your code.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Availability = ({tags}) => {
  const tagTypes = {
    invite: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    beta: {
      styles: "border border-zinc-500/20 bg-zinc-50/50 dark:border-zinc-500/30 dark:bg-zinc-500/10 text-zinc-900 dark:text-zinc-200"
    },
    vscode: {
      styles: "border border-sky-500/20 bg-sky-50/50 dark:border-sky-500/30 dark:bg-sky-500/10 text-sky-900 dark:text-sky-200"
    },
    jetbrains: {
      styles: "border border-amber-500/20 bg-amber-50/50 dark:border-amber-500/30 dark:bg-amber-500/10 text-amber-900 dark:text-amber-200"
    },
    vim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    neovim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    default: {
      styles: "bg-gray-200"
    }
  };
  return <div className="flex items-center space-x-2 border-b pb-4 border-gray-200 dark:border-white/10">
      <span className="text-sm font-medium">Availability</span>
      {tags.map(tag => {
    const tagType = tagTypes[tag] || tagTypes.default;
    return <div key={tag} className={`px-2 py-0.5 rounded-md text-xs font-medium ${tagType.styles}`}>
            {tag}
          </div>;
  })}
    </div>;
};

<Availability tags={["vscode",]} />

## About Instructions

Augment's Instructions let you use natural language prompts to insert new code or modify your existing code. Instructions can be initiated by hitting <Keyboard shortcut="Cmd/Ctrl I" /> and entering an instruction inside the input box that appears in the diff view. The change will be applied as a diff to be reviewed before accepting.

## Using Instructions

To start a new Instruction, there are two options. You can select & highlight the code you want to change or place your cursor where you want new code to be added, then press <Keyboard shortcut="Cmd/Ctrl I" />. You'll be taken to a diff view where you can enter your prompt and see the results.

For example, you can generate new functions based on existing code:

```
> Add a getUser function that takes userId as a parameter
```

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/instructions.png?maxW=1310&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=424409e0c20304b1bb9b668848fd4201" className="rounded-xl" alt="Augment Instructions Diff" width="1310" height="695" data-path="images/instructions.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/instructions.png?w=280&maxW=1310&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=70bbab9b4519ac2c67bf235d42c40395 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/instructions.png?w=560&maxW=1310&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e713c2a24b519c1da4181473c443526d 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/instructions.png?w=840&maxW=1310&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f1d465be0a45fd5bd89c2eb5a8baac23 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/instructions.png?w=1100&maxW=1310&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=9d5ebc5e3f0ea92bec4492873c2d3f5c 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/instructions.png?w=1650&maxW=1310&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=597dd716bf92c2c6b436a899a67550e8 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/instructions.png?w=2500&maxW=1310&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=617d25444f1b26ae35b73b65827256ef 2500w" data-optimize="true" data-opv="2" />

Your change will be made as a diff, so you can review the suggested updates before modifying your code. Use the following shortcuts or click the options in the UI to accept or reject the changes.

<Tabs>
  <Tab title="MacOS">
    | Action            | Shortcut                       |
    | :---------------- | :----------------------------- |
    | Start instruction | <Keyboard shortcut="Cmd I" />  |
    | Accept            | <Keyboard shortcut="Return" /> |
    | Reject            | <Keyboard shortcut="Esc" />    |
  </Tab>

  <Tab title="Windows/Linux">
    | Action            | Shortcut                       |
    | :---------------- | :----------------------------- |
    | Start instruction | <Keyboard shortcut="Ctrl I" /> |
    | Accept            | <Keyboard shortcut="Return" /> |
    | Reject            | <Keyboard shortcut="Esc" />    |
  </Tab>
</Tabs>


# Next Edit
Source: https://docs.augmentcode.com/using-augment/next-edit

Use Next Edit to flow through complex changes across your codebase. Cut down the time you spend on repetitive work like refactors, library upgrades, and schema changes.


export const NextEditSettingsIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg width="16" height="16" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" fill="currentColor">
    <path fill-rule="evenodd" clip-rule="evenodd" d="M19.85 8.75l4.15.83v4.84l-4.15.83 2.35 3.52-3.43 3.43-3.52-2.35-.83 4.15H9.58l-.83-4.15-3.52 2.35-3.43-3.43 2.35-3.52L0 14.42V9.58l4.15-.83L1.8 5.23 5.23 1.8l3.52 2.35L9.58 0h4.84l.83 4.15 3.52-2.35 3.43 3.43-2.35 3.52zm-1.57 5.07l4-.81v-2l-4-.81-.54-1.3 2.29-3.43-1.43-1.43-3.43 2.29-1.3-.54-.81-4h-2l-.81 4-1.3.54-3.43-2.29-1.43 1.43L6.38 8.9l-.54 1.3-4 .81v2l4 .81.54 1.3-2.29 3.43 1.43 1.43 3.43-2.29 1.3.54.81 4h2l.81-4 1.3-.54 3.43 2.29 1.43-1.43-2.29-3.43.54-1.3zm-8.186-4.672A3.43 3.43 0 0 1 12 8.57 3.44 3.44 0 0 1 15.43 12a3.43 3.43 0 1 1-5.336-2.852zm.956 4.274c.281.188.612.288.95.288A1.7 1.7 0 0 0 13.71 12a1.71 1.71 0 1 0-2.66 1.422z" />
    </svg>
  </div>;

export const NextEditDiffIcon = () => <div className="inline-block w-4 h-4 mr-2">
    <svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" viewBox="0 0 16 16">
    <path fill-rule="evenodd" clip-rule="evenodd" d="M10.7099 1.28902L13.7099 4.28902L13.9999 4.99902V13.999L12.9999 14.999H3.99994L2.99994 13.999V1.99902L3.99994 0.999023H9.99994L10.7099 1.28902ZM3.99994 13.999H12.9999V4.99902L9.99994 1.99902H3.99994V13.999ZM8 5.99902H6V6.99902H8V8.99902H9V6.99902H11V5.99902H9V3.99902H8V5.99902ZM6 10.999H11V11.999H6V10.999Z" />
    </svg>
  </div>;

export const NextEditPencil = () => <div className="inline-block w-4 h-4 mr-2">
    <svg width="16px" height="16px" viewBox="0 0 16 16" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
    <title>nextedit_available_dark</title>
    <g id="nextedit_available_dark" stroke="none" stroke-width="1" fill="none" fill-rule="evenodd">
        <path d="M11.0070258,7 C11.1334895,7 11.2318501,6.90866511 11.2529274,6.76814988 C11.5409836,4.95550351 11.8641686,4.52693208 13.7751756,4.2529274 C13.9156909,4.23185012 14,4.13348946 14,4 C14,3.8735363 13.9156909,3.77517564 13.7751756,3.75409836 C11.8571429,3.48009368 11.618267,3.07259953 11.2529274,1.21779859 C11.2248244,1.09133489 11.1334895,1 11.0070258,1 C10.8735363,1 10.7751756,1.09133489 10.7540984,1.22482436 C10.4660422,3.07259953 10.1498829,3.48009368 8.23887588,3.75409836 C8.09836066,3.78220141 8.00702576,3.8735363 8.00702576,4 C8.00702576,4.13348946 8.09836066,4.23185012 8.23887588,4.2529274 C10.1569087,4.52693208 10.4028103,4.92740047 10.7540984,6.77517564 C10.7822014,6.91569087 10.8805621,7 11.0070258,7 Z" id="Path" fill="#BF5AF2"></path>
        <path d="M14.0056206,8.8 C14.0814988,8.8 14.1405152,8.74519906 14.1531616,8.66088993 C14.3259953,7.57330211 14.5199063,7.31615925 15.6665105,7.15175644 C15.7508197,7.13911007 15.8014052,7.08009368 15.8014052,7 C15.8014052,6.92412178 15.7508197,6.86510539 15.6665105,6.85245902 C14.5156909,6.68805621 14.3723653,6.44355972 14.1531616,5.33067916 C14.1362998,5.25480094 14.0814988,5.2 14.0056206,5.2 C13.9255269,5.2 13.8665105,5.25480094 13.8538642,5.33489461 C13.6810304,6.44355972 13.4913349,6.68805621 12.3447307,6.85245902 C12.2604215,6.86932084 12.2056206,6.92412178 12.2056206,7 C12.2056206,7.08009368 12.2604215,7.13911007 12.3447307,7.15175644 C13.4955504,7.31615925 13.6430913,7.55644028 13.8538642,8.66510539 C13.870726,8.74941452 13.9297424,8.8 14.0056206,8.8 Z" id="Path-Copy" fill="#BF5AF2" opacity="0.600000024"></path>
        <g id="Pencil_Base" fill="#168AFF">
            <path d="M3.07557525,3.27946831 C3.10738379,3.27258798 3.13664209,3.26682472 3.16597818,3.26160513 C3.19407786,3.25661079 3.22181021,3.25217747 3.24959807,3.24822758 C3.3431507,3.23490837 3.43787348,3.22705558 3.53270619,3.22474499 C3.54619312,3.22441336 3.56021661,3.22418981 3.57424082,3.22408741 L3.59202055,3.22402251 C3.61600759,3.22402251 3.63999463,3.22437692 3.66397314,3.22508575 C3.69176119,3.22590043 3.72012236,3.22722855 3.74845755,3.22905289 C3.77692744,3.23089046 3.80498198,3.23319023 3.83299719,3.23597733 C3.86236278,3.23889105 3.89230728,3.24242516 3.92218997,3.24651769 C3.95842477,3.25149198 3.99379267,3.25714552 4.02904516,3.2635852 C4.04457753,3.26641925 4.06056799,3.26950351 4.07653203,3.27274998 C4.1217801,3.28195855 4.16647313,3.29238022 4.21089814,3.30408537 C4.22093231,3.3067264 4.23153789,3.30959531 4.24212737,3.31253756 C4.27196202,3.32083528 4.30106886,3.32952376 4.33003598,3.33877116 C4.35855924,3.347869 4.38751122,3.35771229 4.41630528,3.3681193 C4.42116985,3.36987869 4.42551008,3.37146263 4.42984665,3.3730594 C4.4761162,3.39008583 4.52241276,3.4087674 4.56821184,3.42893807 C4.59406406,3.44033198 4.61917606,3.45191971 4.64412424,3.46396063 C4.67111495,3.47697976 4.69839649,3.4907848 4.72546291,3.50513959 C4.75890801,3.52288219 4.79178851,3.54132453 4.82431475,3.56059431 C4.8374698,3.56838641 4.85073285,3.5764165 4.86393439,3.58458539 C4.89491851,3.60376145 4.92539479,3.6235868 4.95550936,3.64416832 C4.9772823,3.65904443 4.99913454,3.67451232 5.02078256,3.69038541 C5.03998798,3.70447076 5.05881967,3.71870909 5.07748715,3.73325923 C5.10440445,3.75423289 5.13126725,3.7760983 5.15775949,3.79862613 C5.1821715,3.81939236 5.20595148,3.84042939 5.22940861,3.86201411 C5.24512436,3.87647694 5.26059993,3.89109333 5.27592752,3.90595256 C5.28442786,3.91418351 5.29385225,3.92345739 5.30321896,3.9328241 L10.2031018,8.83270693 C10.255475,8.88508012 10.3065885,8.93859789 10.3564099,8.99321224 L10.2031018,8.83270693 C10.2748395,8.90444467 10.344214,8.97832987 10.4111413,9.05423915 C10.4223877,9.06699478 10.4335715,9.07981507 10.4446856,9.092692 C10.7663645,9.46539004 11.0297601,9.88553066 11.2252237,10.3388957 L11.6780206,11.3880225 L12.548286,13.4076516 C12.7467158,13.8678966 12.5344727,14.4018581 12.0742277,14.6002879 C11.9977866,14.6332447 11.9179446,14.6552159 11.836969,14.6662015 L11.7149387,14.6744406 C11.592625,14.6744406 11.4703113,14.6497231 11.3556497,14.6002879 L11.2340206,14.5480225 L9.33602055,13.7300225 L8.28689372,13.2772256 C7.83352871,13.081762 7.41338809,12.8183665 7.04069004,12.4966876 L7.0022372,12.4631433 C6.98177889,12.4451057 6.9614676,12.4268903 6.94130575,12.4084989 L7.04069004,12.4966876 C6.95122931,12.4194733 6.86450207,12.3389008 6.78070498,12.2551038 L1.88082214,7.35522092 C0.935753358,6.41015213 0.935753358,4.87789288 1.88082214,3.9328241 L1.90902055,3.90502251 L2.01192506,3.8109306 C2.19120357,3.65606766 2.38780913,3.5318516 2.59488381,3.4382824 C2.62872186,3.42311621 2.65522016,3.41182111 2.68187195,3.40102033 C2.76025666,3.36925866 2.83986347,3.34180278 2.92043821,3.31861145 L3.07557525,3.27946831 Z M9.58610551,9.95149698 L7.89951995,11.6381324 C8.10279642,11.805046 8.32371441,11.9494547 8.55841217,12.068738 L8.76594574,12.166096 L10.2570206,12.8090225 L10.7570206,12.3090225 L10.114094,10.8179477 C9.97930356,10.5053101 9.80144069,10.2137385 9.58610551,9.95149698 Z" id="Combined-Shape" fill-rule="nonzero"></path>
            <rect id="Rectangle" opacity="0.005" x="0" y="0" width="16" height="16" rx="2"></rect>
        </g>
    </g>
    </svg>
  </div>;

export const Availability = ({tags}) => {
  const tagTypes = {
    invite: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    beta: {
      styles: "border border-zinc-500/20 bg-zinc-50/50 dark:border-zinc-500/30 dark:bg-zinc-500/10 text-zinc-900 dark:text-zinc-200"
    },
    vscode: {
      styles: "border border-sky-500/20 bg-sky-50/50 dark:border-sky-500/30 dark:bg-sky-500/10 text-sky-900 dark:text-sky-200"
    },
    jetbrains: {
      styles: "border border-amber-500/20 bg-amber-50/50 dark:border-amber-500/30 dark:bg-amber-500/10 text-amber-900 dark:text-amber-200"
    },
    vim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    neovim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    default: {
      styles: "bg-gray-200"
    }
  };
  return <div className="flex items-center space-x-2 border-b pb-4 border-gray-200 dark:border-white/10">
      <span className="text-sm font-medium">Availability</span>
      {tags.map(tag => {
    const tagType = tagTypes[tag] || tagTypes.default;
    return <div key={tag} className={`px-2 py-0.5 rounded-md text-xs font-medium ${tagType.styles}`}>
            {tag}
          </div>;
  })}
    </div>;
};

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

<Availability tags={["vscode"]} />

## About Next Edit

<iframe class="w-full aspect-video rounded-md" src="https://www.youtube.com/embed/GPQgQpXbunc?si=opEGaxWlnWWtDimK" title="Feature Intro: Augment Next Edit" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen />

Next Edit helps you complete your train of thought by suggesting changes based on
your recent work and other context. You can jump to the next edit and quickly accept or
reject the suggested change with a single keystroke.

## Using Next Edit

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-example.webp?maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=652e0ea41f4a43f9e5907df60157478c" className="rounded-xl" width="800" height="269" data-path="images/next-edit-example.webp" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-example.webp?w=280&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=abc999c08f4876bbcc143f08a62caa7a 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-example.webp?w=560&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=df9ffc2afcefc70804ebf6298482d825 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-example.webp?w=840&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=05b4977f32f321aeb798b0e8c911aea1 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-example.webp?w=1100&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c453272dab4c6c6dbc35d92b62edd47f 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-example.webp?w=1650&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=475bc01478a480426c138d7bb619ed47 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-example.webp?w=2500&maxW=800&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b2ab65a168b726e1b2810fb7f741896e 2500w" data-optimize="true" data-opv="2" />

When Next Edit has a suggestion available, you will see a gutter icon and a summary
of the change in gray at the end of the line.
To jump to the next suggestion, press <Keyboard shortcut="Cmd/Ctrl ;" /> and
after reviewing the change, press <Keyboard shortcut="Enter" /> to accept
or <Keyboard shortcut="Backspace" /> to reject. If there are multiple
changes, press <Keyboard shortcut="Cmd/Ctrl ;" /> to accept and go to the
next suggestion.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-before.png?maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=cb618ab9181c2d32ff1f8e7fa2e5d99b" className="rounded-xl" width="1462" height="447" data-path="images/next-edit-before.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-before.png?w=280&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=8d1b54cd2c15f57bfdff71431f0bbcf2 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-before.png?w=560&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b0c671ba82bb8b5830d06ee7da952704 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-before.png?w=840&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b651f24f7398ca3503dcbd398035c034 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-before.png?w=1100&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=383e73d134975e8fe4f89cd5bfd2ff4e 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-before.png?w=1650&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=2d9d1fb8e951f29be479128480eeb10d 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-before.png?w=2500&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=e95799bc18fcb1dd3633ae5c0351497d 2500w" data-optimize="true" data-opv="2" />

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-after.png?maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=b87142cd005afb9a62ae564f0a0a0b38" className="rounded-xl" width="1462" height="447" data-path="images/next-edit-after.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-after.png?w=280&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7d41d53fcce25cf59e09607dae13ec7c 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-after.png?w=560&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=4700f37797723b42e862f722a2df1962 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-after.png?w=840&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=31ff0427549fb5165f218378edbfe433 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-after.png?w=1100&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3ce6c4312943ce23b1ac490e4c87fb2e 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-after.png?w=1650&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=fc6765cf963f8369b40cfa7044e6dff4 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-after.png?w=2500&maxW=1462&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=29060153a96869be4fd799afecfce3eb 2500w" data-optimize="true" data-opv="2" />

By default, Next Edit will briefly highlight which parts of the existing code will
change before applying the change and highlighting the new code. Use Undo
(<Keyboard shortcut="Cmd/Ctrl Z" />) and Redo
(<Keyboard shortcut="Cmd Shift Z/Ctrl Y" />) to manually review the change.
You can configure this behavior in your Augment extension settings.

### Keyboard Shortcuts

<Tabs>
  <Tab title="MacOS">
    | Action            | Default shortcut                    |
    | :---------------- | :---------------------------------- |
    | Go to next        | <Keyboard shortcut="Cmd ;" />       |
    | Go to previous    | <Keyboard shortcut="Cmd Shift ;" /> |
    | Accept suggestion | <Keyboard shortcut="Enter" />       |
    | Reject suggestion | <Keyboard shortcut="Backspace" />   |
  </Tab>

  <Tab title="Windows/Linux">
    | Action            | Default shortcut                     |
    | :---------------- | :----------------------------------- |
    | Go to next        | <Keyboard shortcut="Ctrl ;" />       |
    | Go to previous    | <Keyboard shortcut="Ctrl Shift ;" /> |
    | Accept suggestion | <Keyboard shortcut="Enter" />        |
    | Reject suggestion | <Keyboard shortcut="Backspace" />    |
  </Tab>
</Tabs>

### Next Edit Indicators And Actions

There are several indicators to let you know Next Edits are available:

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-1.png?maxW=1321&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=31968956ad3ae7049b794221fd6670b3" className="rounded-xl" width="1321" height="493" data-path="images/next-edit-indicators-1.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-1.png?w=280&maxW=1321&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=603e1e0959bb3c9d17b847edb01650f1 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-1.png?w=560&maxW=1321&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7a68169f8ff968f0e6386ea549581129 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-1.png?w=840&maxW=1321&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=f67285da14d324758a245ac523351822 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-1.png?w=1100&maxW=1321&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=05f0d9fe48e12c848f04c5c01ae63681 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-1.png?w=1650&maxW=1321&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1f075ea4816012df3b4d3059e723e6c6 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-1.png?w=2500&maxW=1321&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=7fb7821a2909838a466bc96b5c59732d 2500w" data-optimize="true" data-opv="2" />

1. **Editor Title Icon** (Top Right): Changes colors when next edits are available.
   Click on the <NextEditPencil /> icon to open the next edit menu for
   additional actions like enabling/disabling the feature or accessing settings.
2. **Gutter Icon** (Left) - Indicates which lines will be changed by the suggestion
   and whether it will insert, delete or change code.
3. **Grey Text** (Right) -  appears on the line with the suggestion on screen with a
   brief summary of the change and the keybinding to press (typically
   <Keyboard shortcut="Cmd/Ctrl ;" />).

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-2.png?maxW=1322&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d5143233db8cd60eaa794b71fb0c0fda" className="rounded-xl" width="1322" height="136" data-path="images/next-edit-indicators-2.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-2.png?w=280&maxW=1322&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=addc9e869d64bd62fe201e62c3c358ba 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-2.png?w=560&maxW=1322&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1285c43d29b4234ca87dfb22c30b7475 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-2.png?w=840&maxW=1322&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=3d6165348b12cb3396d067d6027abfe0 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-2.png?w=1100&maxW=1322&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=d532fead64d92a88355549c7b3491bf3 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-2.png?w=1650&maxW=1322&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=5f89dbb6a2c2d3a6945a6338528d1e79 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/next-edit-indicators-2.png?w=2500&maxW=1322&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c4b0e98985aac0f2a5becd38a6dc5972 2500w" data-optimize="true" data-opv="2" />

4. **Hint Box** (Bottom Left) - appears when the next suggestion is off screen with
   brief summary of the change and the keybinding to press (typically
   <Keyboard shortcut="Cmd/Ctrl ;" />).

The tooltip also presents a few actions as icons:

* <NextEditDiffIcon /> Toggles showing diffs for suggestions in the tooltip.
* <NextEditSettingsIcon /> Opens Next Edit settings.

### Next Edit Settings

You can configure Next Edit settings in your Augment extension settings.
To open Augment extension settings, either navigate to the option through the pencil
menu, or open the Augment Commands panel by pressing
<Keyboard shortcut="Cmd/Ctrl Shift A" /> and select <Command text="⚙ Edit Settings" />.

Here are some notable settings:

* <Command text="Augment > Next Edit: Enable Background Suggestions" />: Use to enable or
  disable the feature.
* <Command text="Augment > Next Edit: Enable Global Background Suggestions" />: When enabled, Next
  Edits will suggest changes in other files via the hint box.
* <Command text="Augment > Next Edit: Enable Auto Apply" />: When enabled, Next
  Edits will automatically apply changes when you jump to them.
* <Command text="Augment > Next Edit: Show Diff in Hover" />: When enabled,
  Next Edits will show a diff of the suggested change in the hover.
* <Command text="Augment > Next Edit: Highlight Suggestions in The Editor" />: When enabled,
  Next Edits will highlight all lines with a suggestion in addition to showing gutter
  icons and grey text.


# Using Remote Agent
Source: https://docs.augmentcode.com/using-augment/remote-agent

Use Remote Agent to complete tasks across your workflow–implementing a feature, upgrade a dependency, or writing a pull request–all from the cloud and with the full power of Visual Studio Code when you need it.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About Remote Agent

Augment Remote Agent is a powerful tool that can help you complete software development tasks end-to-end that runs in a secure, cloud environment. You can run multiple agents in parallel on independent tasks, and you'll monitor and manage their progress from within Visual Studio Code. Remote Agents can run in normal or auto mode, just like IDE-based agents, and will notify you when they need attention.

### How is Remote Agent different from Agent?

Remote Agent is a cloud version of the IDE-bound Agent. Each Remote Agent runs on its own secure environment, with its own workspace-all of which is managed for you. Each Remote Agent works independently and on its own branch, so you can have multiple agents working on the same repository at the same time.

## Accessing Remote Agent

To start a new Remote Agent, simply open the Augment panel and select Remote Agent from the drop down in the input box.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-selector.png?maxW=1400&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=50b156d520d82a02c5dbbbfd85e25eab" alt="Augment Remote Agent" className="rounded-xl" width="1400" height="738" data-path="images/remote-agent-selector.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-selector.png?w=280&maxW=1400&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3938d0de1b6e57ed7220e49263f5937f 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-selector.png?w=560&maxW=1400&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=ed4b2d19f0c4d4dc65058ae871b6318a 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-selector.png?w=840&maxW=1400&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=1f35af79bc0ca808df32d182791d3691 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-selector.png?w=1100&maxW=1400&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c870de22bd1bbbd29b1693e3b69e386f 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-selector.png?w=1650&maxW=1400&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a00e5f4df00ca307fb32e37a04a564e2 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-selector.png?w=2500&maxW=1400&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=5d3b8d7aeb4235fadb6f2d8eddaa4fbb 2500w" data-optimize="true" data-opv="2" />

### Agent dashboard

You can view all of your remote agents in the Remote Agent dashboard by clicking the <Command text="Expand dashboard" /> icon in the top of the Augment panel. From the dashboard you are able to see the status of all of your agents, connect to them through SSH, or delete them when they are no longer needed.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-dashboard.png?maxW=1134&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d4da0d494ef66a64b26a38737f25253d" alt="Augment Agent" className="rounded-xl" width="1134" height="640" data-path="images/remote-agent-dashboard.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-dashboard.png?w=280&maxW=1134&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=2a10ee4b7a005cd39524b5ed7b3233a7 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-dashboard.png?w=560&maxW=1134&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=de765a2f1e05922d9138f8e787ad1ab5 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-dashboard.png?w=840&maxW=1134&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=9d7681c2cbf697e56c74ac61095dc0fb 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-dashboard.png?w=1100&maxW=1134&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4c6bdb4c6c30a82e1d9ad1324d9bd97c 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-dashboard.png?w=1650&maxW=1134&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=cce582c4d140ace781f8a609dcbeae01 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-dashboard.png?w=2500&maxW=1134&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e6350ddeb31fd50e907e7f120c6087bf 2500w" data-optimize="true" data-opv="2" />

## Using Remote Agent

Remote Agents function nearly identically to IDE-bound agents as you work through your tasks and projects. Because they run asynchronously in the cloud, you can access and manage them while working on other projects in your editor. Access your Remote Agents from the threads menu at the top of the Augment panel or through the Remote Agent dashboard.

You can create and manage a Remote Agent for any repository you have access to through GitHub regardless of which project you are currently working on in your editor.

### Create a remote agent

<Note>
  Before you can use Remote Agent, you will need to connect your GitHub account to enable the agent to clone your repository, create branches, and open pull requests. See [Agent Integrations](/setup-augment/agent-integrations) for setup instructions.
</Note>

1. **Select the repository** you want the agent to work on
2. **Select the branch** or let the agent create a new branch for you
3. **Select an environment** or [create a new one](/using-augment/remote-agent-environment) for the agent to run in
4. Enter your prompt into the input box using natural language and click **Create agent**

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-new.png?maxW=962&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=5e861b4ba6641952a72bcca76fd268a0" alt="Create a Remote Agent" className="rounded-xl" width="962" height="950" data-path="images/remote-agent-new.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-new.png?w=280&maxW=962&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=78ee79135c0862f9ecd2f92c65ccd2e7 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-new.png?w=560&maxW=962&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=37f2784d9270328077e88d916a2700da 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-new.png?w=840&maxW=962&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=735c4e9ddb01c142dfe3834667d58892 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-new.png?w=1100&maxW=962&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3cd325dcbfa32c42e3337125bd08cb2e 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-new.png?w=1650&maxW=962&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=588be2408b58ae108da91439f77189c0 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-new.png?w=2500&maxW=962&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=0788e7a4bce69d34e3d1769d426edfbc 2500w" data-optimize="true" data-opv="2" />

#### Agent environment

Each Remote Agent runs in an secure, independent environment in the cloud. This enables each agent to have its own workspace, copy of the repository, and virtualized operating system to run other tools and commands. You can use the [base environment](/using-augment/remote-agent-environment#base-environment), or setup a custom environment using a bash script to configure the tools the agent will need to complete the task.

See [Remote Agent Environment](/using-augment/remote-agent-environment) for more details on customizing the agent environment.

### Agent notifications

By default, you will receive a notification in VS Code when the agent has completed a task or needs your attention. You can disable notifications for a remote agent by clicking the bell icon in the theads list of the Augment panel.

### Iterating with an agent

Once an agent has completed the task, you can continue to iterate with the agent by sending additional messages. The agent will continue to work on the task, using its past conversations as context. If you need to switch to editing files directly, you can connect to the agent environment over SSH. See [Connecting to a Remote Agent](#connecting-to-a-remote-agent-environment) for more details.

### Reviewing changes

You can review every change Agent makes by clicking on the action to expand the view. Review diffs for file changes, see complete terminal commands and output, and the results of external integration calls.

<img src="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=992e233d6c319b35fda89cce50ffd480" alt="Augment Agent" className="rounded-xl" width="1235" height="543" data-path="images/agent-edit.png" srcset="https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=280&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=de3af323730e413ae5aa068f45f96d69 280w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=560&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=a21dda07e1990ee1ce08d78cfa4d927d 560w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=840&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=1d204328804871ef7aeffb148b23674e 840w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=1100&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=6e1f4b4037e539116b27598a96dc992c 1100w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=1650&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=10dd9f8c50efdf339e6a430f7378ae68 1650w, https://mintcdn.com/augment-mtje7p526w/r-azeXhOS4FbEUi5/images/agent-edit.png?w=2500&maxW=1235&auto=format&n=r-azeXhOS4FbEUi5&q=85&s=c2942a51e3c30b108c4a52d572083179 2500w" data-optimize="true" data-opv="2" />

### Stop or guide the Agent

You can interrupt the Agent at any time by clicking Stop. This will pause the action to allow you to correct something you see the agent doing incorrectly. While Agent is working, you can also prompt the Agent to try a different approach which will automatically stop the agent and prompt it to correct its course.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-stop.png?maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=17198f943f16cfe350a3a2739341856a" alt="Stopping the agent" className="rounded-xl" width="1290" height="574" data-path="images/remote-agent-stop.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-stop.png?w=280&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=0c1d168837d5c1f064649318d13693fa 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-stop.png?w=560&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=beccaefb2548abf3171d66f27605d305 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-stop.png?w=840&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=16ecbc88e3b016710a24c0bb2889e0f9 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-stop.png?w=1100&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=5f9a026539af87386ca04cf3ece1c54e 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-stop.png?w=1650&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=ba25fbd68754fe6b166c313786eddcee 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-stop.png?w=2500&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=043c970ec3fe567a8f9973cf98adce85 2500w" data-optimize="true" data-opv="2" />

### Connecting to a Remote Agent environment

<Note>
  You will need to have the [Remote-SSH extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-ssh) installed in Visual Studio Code to connect to a remote agent. If you do not have it installed, you will be prompted to install it automatically.
</Note>

From time to time you may need to connect to a remote agent to view or edit files directly, in that case you can connect to the agent environment over SSH. From the Remote Agent dashboard, click the <Command text="SSH to agent" /> button in the agent card you with to connect to.

This will open a Visual Studio Code window connected to the agent's environment. If this is your first time opening the connection, you will be prompted by VS Code to trust the files in the remote folder. Click <Command text="Yes, I trust the authors" /> to continue.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-trust.png?maxW=1362&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=44bbf9d2bc3e233073e29d67a72b5f2a" alt="Augment Agent" className="rounded-xl" width="1362" height="816" data-path="images/remote-agent-trust.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-trust.png?w=280&maxW=1362&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b75bb1d2c48fafcd50dbf0473a43e55a 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-trust.png?w=560&maxW=1362&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=09ba20fbaaf0131c4b449d7b6de22152 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-trust.png?w=840&maxW=1362&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3e6335b258d6f8c61db2ff91ddb4633f 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-trust.png?w=1100&maxW=1362&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d9324ad346b50f7e21f338603c48d150 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-trust.png?w=1650&maxW=1362&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e086b63b9d4ad3ae1d59d921097cf0b6 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-trust.png?w=2500&maxW=1362&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=60f9da6137fdd40d671adfac0e68decc 2500w" data-optimize="true" data-opv="2" />

You can use the new VS Code window to view and edit files, run commands in the terminal, and generally interact with the agent just like you would a local IDE-bound agent.

### Opening a Pull Request

When the agent has completed the work, you can open a pull request to have your changes opened for review and merging into the main branch. Select the agent from the threads list and click <Command text="Create a PR" />. The agent will create a branch, commit the changes, and open a pull request for you. This will send a user message that will count against your quota.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-pr.png?maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=fba7582d9b4c04e4d31dfccb88a35e8e" alt="Augment Agent Pull Request" className="rounded-xl" width="1290" height="962" data-path="images/remote-agent-pr.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-pr.png?w=280&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=396e6453c79fdf362396a047878c55dc 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-pr.png?w=560&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=0da8e5f2461af86fe8fd7d7a96495067 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-pr.png?w=840&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b2793c2ffc0de783a9c52ba119648bbd 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-pr.png?w=1100&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=738e39377d5cd4840b69cb60700a8e55 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-pr.png?w=1650&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=711e06924c53c96ecaea8807436dd150 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/remote-agent-pr.png?w=2500&maxW=1290&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=d54300e41d12422ba9ed683f9028fedf 2500w" data-optimize="true" data-opv="2" />

### Resuming a Remote Agent

Remote Agents automatically pause after completing a request or remaining idle for a period of time. To resume a paused Remote Agent, either click <Command text="Open a remote workspace" /> or send a new message to the agent. Both actions will count against your user message quota.

## Comparison chart

Agent takes Chat to the next level by allowing Augment to do things for you-that is create and make modifications directly to your codebase. Chat can explain code, create plans, and suggest changes which you can smartly apply one-by-one, but Agent takes it a step further by automatically implementing the entire plan and all code changes for you.

| What are you trying to do?                       | Chat | Agent | Remote Agent |
| :----------------------------------------------- | :--: | :---: | :----------: |
| Ask questions about your code                    |  ☑️  |   ✅   |       ✅      |
| Get advice on how to refactor code               |  ☑️  |   ✅   |       ✅      |
| Add new features to selected lines of code       |  ☑️  |   ✅   |       ✅      |
| Add new feature spanning multiple files          |      |   ✅   |       ✅      |
| Document new features                            |      |   ✅   |       ✅      |
| Open Linear tickets or start a pull request      |      |   ✅   |       ✅      |
| Start a new branch in GitHub from recent commits |      |   ✅   |       ✅      |
| Automatically perform tasks on your behalf       |      |   ✅   |       ✅      |
| Work on multiple tasks in the same repository    |      |       |       ✅      |
| Continue working after closing VS Code           |      |       |       ✅      |

## Use cases

Use Remote Agent to handle various aspects of your software development workflow, from simple configuration changes to feature implementations. Remote Agent is best for discreet tasks that can be completed in isolation from other work. Remote Agent supports your daily engineering tasks like:

* **Make quick edits** - Create a pull request to adjust configuration values like feature flags from FALSE to TRUE
* **Fix papercuts** - Fix small bugs or issues in the codebase that never make it to the top of your TODO list
* **Perform refactoring** - Move functions between files while maintaining coding conventions and ensuring bug-free operation
* **Explore alternatives** - Run multiple remote agents to create alternative solutions to a problem
* **Start a first draft for new features** - Start a pull request (PR) with implementing entirely new functionality straight from a GitHub Issue or Linear Ticket
* **Start tickets in Linear or Jira** - Open tickets and ask Agent to suggest a plan to address the ticket
* **Create test coverage** - Generate unit tests for your newly developed features
* **Generate documentation** - Produce comprehensive documentation for your libraries and features

## Remote Agent Clean-up

Remote Agents automatically pause after completing a request or remaining idle for a period of time. Agents that remain idle for 30 days are automatically cleaned up by the system. This cleanup process removes all files in the Remote Workspace, conversation history, and any pending diffs.

## Next steps

* [Configure Agent Integrations](/setup-augment/agent-integrations)
* [Configure other tools with MCP](/setup-augment/mcp)


# Using Augment for Slack
Source: https://docs.augmentcode.com/using-augment/slack

Chat with Augment directly in Slack to explore your codebase, get instant help, and collaborate with your team on technical problems.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## About Augment for Slack

Augment for Slack brings the power of Augment Chat to your team's Slack workspace. Mention <Command text="@Augment" /> in any channel or start a DM with Augment to have deep codebase-aware conversations with your team. Before you can use Augment for Slack, you will need to [install the Augment Slack App](/setup-augment/install-slack-app).

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/slack-chat-reply.png?maxW=1544&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=433c3dd9b6e71b18bdaeea05ce808971" alt="Augment for Slack" className="rounded-xl" width="1544" height="866" data-path="images/slack-chat-reply.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/slack-chat-reply.png?w=280&maxW=1544&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=cc091c700ccdb6819385a49ca1b2c8cb 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/slack-chat-reply.png?w=560&maxW=1544&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e2516c310bef6200acf438b1c9321450 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/slack-chat-reply.png?w=840&maxW=1544&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=6f9398a528968db81785752013d2639b 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/slack-chat-reply.png?w=1100&maxW=1544&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=1ede5c3e3e005b278380a6e923271b93 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/slack-chat-reply.png?w=1650&maxW=1544&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=fd345381266192e34411dfe7fe1883e2 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/slack-chat-reply.png?w=2500&maxW=1544&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=f975c93b6d8bd5b9f573ae19eef3edcc 2500w" data-optimize="true" data-opv="2" />

## Adding Augment to Channels

Mention <Command text="@Augment" /> to add it to any public or private channel.

*Note: To protect your code, Augment excludes repository context in channels with external members.*

## Starting Conversations in Channels

Mention <Command text="@Augment" /> anywhere in your message or thread to start a conversation. Augment will consider the entire thread's context when responding. Remove messages by adding a ❌ reaction.

## Direct Messages

While group discussions help share knowledge, you can also have private conversations with Augment. Access it by:

* Clicking the Augment logo in the top right of your Slack workspace
* Finding it under <Command text="Apps" /> in the Slack sidebar
* Pressing <Keyboard shortcut="Cmd/Ctrl T" /> and searching for <Command text="@Augment" />

If you don't see the Augment logo, add it to your [navigation bar](/setup-augment/install-slack-app#3-add-augment-to-the-slack-navigation-bar). *If you don't see this option, contact your workspace admin to [re-install the App](/setup-augment/install-slack-app#2-install-slack-app).*

You do not need to mention Augment in direct messages - it will respond to every message!

## Restricting where Augment can be used

Augment already avoids responding with codebase context in external channels, to protect your codebase from Slack users outside of your organization. Beyond this, you can also further restrict what channels Augment can be used in, with an allowlist. If configured, Augment will only respond in channels or DMs that are in the allowlist. To use this feature, contact us.

## Repository Context

Augment uses the default branch (typically `main`) of your linked repositories. Currently, other branches aren't accessible.

If you have multiple repositories installed, use <Command text="/augment repo-select" /> to choose which repository Augment should use for the current conversation. This selection applies to the specific channel or DM where you run the command, allowing you to work with different repositories in different conversations.

## Feedback

Help us improve by reacting with 👍 or 👎 to Augment's responses, or use the `Send feedback` message shortcut. We love hearing from you!


# Using Tasklist
Source: https://docs.augmentcode.com/using-augment/tasklist

Use Tasklist to break down complex problems into manageable steps, track progress, and collaborate with Agent on multi-step tasks.

## About the Tasklist?

Augment's Tasklist helps the Agent in the IDE create and refine a step-by-step plan for you to review. The Tasklist provides a structured interface for collaboration between you and the Agent, allowing you to break down complex problems into manageable, sequential steps.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=7b57f10306d17d7a01769a36f1f08888" alt="Tasklist Overview" className="rounded-xl" width="473" height="208" data-path="images/tasklist-overview.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=cfe6643999d0f51858bdc307a405e706 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=707d717d48b17655f8de15a57e17efb2 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=28a71d28a31963133145d84dd4c6dc6e 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=2d8afe47cdba513cacd3b1510212c099 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=fb50e40cef51f5c43b392b283ac52626 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-overview.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=2b21a1b7e583664dc6eac0559d0129ac 2500w" data-optimize="true" data-opv="2" />

## Getting started with Tasklist?

Tasklist improves agent effectiveness on long or complex tasks by:

* **Maintaining context** across different conversations by moving your Tasklist to a new chat
* **Breaking down complex problems** into manageable, sequential steps
* **Gathering progress** across threads
* **Exploring alternative solutions** to completed tasks if you need to pivot
* **Streamlining your approach** to nebulous problems by deleting irrelevant steps once the path forward is clear

Tasklist provides a structured interface for collaboration and opens up possibilities for agent-to-agent collaboration. We hypothesize that an interface such as Tasklist could be a preferred way to interact with coding agents in the future.

## Creating a New Task

### Automatic Creation

The Agent will usually create a Tasklist when it encounters a complex, multi-step problem. You can also ask the Agent to make a Tasklist for you by simply prompting "Start a Tasklist to..." then add the problem you are trying to tackle.

### Manual Creation

You can also manually create a Tasklist:

1. Switch to Tasklist using the checklist button next to Changes
2. Click the plus to add your first task
3. Alternatively, you can create a new task by typing in the gray prompt box at the bottom of the extension. Click **Add Task** from the dropdown arrow next to Send

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a2603f672d47c74e7582cb6da58cad04" alt="Creating a new task" className="rounded-xl" width="473" height="85" data-path="images/tasklist-create-task.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=273857c88137440b4ce932962d5842d8 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b53633da83f18abacd816c4a4fbb2fe2 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=03e5417ccbd446b8ee6b10fc6b00f2f4 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=2e13079c3e2eabfdde93bb4ed73c3a87 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=34bf7e951951489686422f7cc5ea3b3d 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-create-task.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=bc3db1e1b3dd7c092b91dcdbd38a2561 2500w" data-optimize="true" data-opv="2" />

## Running Tasks

To run a task, click the grey triangle (play button) next to the task. The Agent will begin executing the task and update its status as it progresses.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=58d05e0c445e9b4fb449c6ade5a298bd" alt="Running a task" className="rounded-xl" width="824" height="778" data-path="images/tasklist-run-task.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4819f31c0860ebcc5827693ea0c0baad 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=27aa131b8c5fd591162d6fccfe35ec50 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=8b90fc209a811b5f2f59f9747edce1df 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c05369faa15a20ad17622d875ac2f601 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=6c3c3c9250484b0982d023bbd1400693 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-run-task.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=3de97385af039261f008cfb0e801116d 2500w" data-optimize="true" data-opv="2" />

## Task Status Indicators

Task statuses are indicated by different colors and icons:

* **Empty circle** - Task has not yet started
* **Blue half circle** - Task is currently in progress
* **Green checkbox** - Task has been completed and is ready for review

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=989d263506a6346c0033d5fe0ea51475" alt="Task status indicators" className="rounded-xl" width="473" height="214" data-path="images/tasklist-status-indicators.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=cd926a7cbeb7ec67d4bb51cead1485c6 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=6b2651040fdbad62384eee3cfdbfe716 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=856571460250f49bcabd817161b0f270 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=24e4ac9d6f6290731463213cfad02657 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a1148d6927825479fc4e92dd5da17469 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-status-indicators.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=92da7588be36eeb5b471593b51dcc1c0 2500w" data-optimize="true" data-opv="2" />

## Subtasks

Augment Code automatically generates subtasks when needed. The Agent will automatically add and nest required subtasks under your initial tasks. You can edit and expand these subtasks just like any other task in the list. Likewise, you can remove subtasks you deem unnecessary.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=06a66a68939509b93969d6ee352363a7" alt="Subtasks example" className="rounded-xl" width="233" height="32" data-path="images/tasklist-subtasks.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=64ab84c553e9c00a188211b706e2fac0 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=754a79480312c19f6d2cdfb6f0da568a 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=ed5c411199b3c1c08d194dca0996ba7a 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=c85b03a98902b4200034ffbe772f86aa 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a66ffd3ef9f68064fa3d215b59b8e444 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-subtasks.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=f40745bd17de1648e51d5304d312b67b 2500w" data-optimize="true" data-opv="2" />

## Managing Running Tasks

### Stopping a Task

You can treat any in-progress task like any prompt you might send the Agent. To stop what the Agent is doing and offer a corrective action, click the red square (stop button) and tell the Agent what you want it to do instead.

### Running All Tasks

The Agent can complete all the tasks sequentially by clicking the triangle (play button) at the top of the Tasklist.

## Reviewing Changes

You can review the changes made by the Agent after a task is completed by toggling between the Tasks and Changes view to see the diffs (differences) of the work done by the agent for each task.

<img src="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=35ce060276c5dc8fec9f1f9b473c9599" alt="Reviewing changes in Tasks and Changes view" className="rounded-xl" width="818" height="364" data-path="images/tasklist-changes-view.png" srcset="https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=280&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=7c4571f3c0ead8a670ca3aa604176d0c 280w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=560&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=4479c4f468883c3a59feed2560c9a81c 560w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=840&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=a649dcd4a9164c2eeb3d5928ba4b5e40 840w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=1100&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=e85d1a4989fd58ab60e561f1a38fb8d3 1100w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=1650&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=b563421017b53c86cb7704e7f5369ab2 1650w, https://mintcdn.com/augment-mtje7p526w/IEgTogsPIebDB-Bu/images/tasklist-changes-view.png?w=2500&fit=max&auto=format&n=IEgTogsPIebDB-Bu&q=85&s=364274422e2215186f8b207441307ec9 2500w" data-optimize="true" data-opv="2" />

## Integration with Task Management Tools

### Jira and Linear Integration

The Tasklist is a perfect pairing with existing task management tools like Jira or Linear:

* Ask the Agent to create a Tasklist based on tickets inside Jira or Linear
* Further break down complex tickets into manageable steps
* Once your Tasklist is completed, you can ask the Agent to resolve the issue inside Jira or Linear and append the steps taken as a comment

### Standalone Usage

Don't use an issue tracker? No problem - use Tasklist to track issues you need to tackle across Threads.

## Best Practices

* **Be specific** when creating tasks to help the Agent understand exactly what needs to be done
* **Review and edit** the automatically generated subtasks to ensure they align with your goals
* **Use the stop function** to provide course corrections when the Agent is heading in the wrong direction
* **Leverage the Changes view** to review all modifications made during task execution
* **Move Tasklists** between conversations to maintain context across different chat sessions

## Next Steps

* [Learn more about Agent](/using-augment/agent)
* [Configure Agent Integrations](/setup-augment/agent-integrations)


# Install Augment for Vim and Neovim
Source: https://docs.augmentcode.com/vim/setup-augment/install-vim-neovim

Augment for Vim and Neovim gives you powerful code completions and chat capabilities integrated into your favorite code editor.

export const Next = ({children}) => <div className="border-t border-b pb-8 border-gray dark:border-white/10">
    <h3>Next steps</h3>
    {children}
  </div>;

export const NeoVimLogo = () => <svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
<g clip-path="url(#clip0_1012_311)">
<path fill-rule="evenodd" clip-rule="evenodd" d="M2.11719 5.0407L7.2509 -0.14502V23.9669L2.11719 18.841V5.0407Z" fill="url(#paint0_linear_1012_311)" />
<path fill-rule="evenodd" clip-rule="evenodd" d="M21.9551 5.08747L16.7572 -0.14502L16.8625 23.9669L21.9902 18.8404L21.9551 5.08747Z" fill="url(#paint1_linear_1012_311)" />
<path fill-rule="evenodd" clip-rule="evenodd" d="M7.25 -0.111816L20.5981 20.2637L16.8629 24.0001L3.50781 3.66964L7.25 -0.111816Z" fill="url(#paint2_linear_1012_311)" />
<path fill-rule="evenodd" clip-rule="evenodd" d="M7.24955 9.28895L7.24248 10.0894L3.14258 4.01872L3.52221 3.63086L7.24955 9.28895Z" fill="black" fill-opacity="0.13" />
</g>
<defs>
<linearGradient id="paint0_linear_1012_311" x1="258.803" y1="-0.14502" x2="258.803" y2="2411.04" gradientUnits="userSpaceOnUse">
<stop stop-color="#16B0ED" stop-opacity="0.800236" />
<stop offset="1" stop-color="#0F59B2" stop-opacity="0.837" />
</linearGradient>
<linearGradient id="paint1_linear_1012_311" x1="-239.663" y1="-0.14502" x2="-239.663" y2="2411.04" gradientUnits="userSpaceOnUse">
<stop stop-color="#7DB643" />
<stop offset="1" stop-color="#367533" />
</linearGradient>
<linearGradient id="paint2_linear_1012_311" x1="858.022" y1="-0.111816" x2="858.022" y2="2411.08" gradientUnits="userSpaceOnUse">
<stop stop-color="#88C649" stop-opacity="0.8" />
<stop offset="1" stop-color="#439240" stop-opacity="0.84" />
</linearGradient>
<clipPath id="clip0_1012_311">
<rect width="24" height="24" fill="white" />
</clipPath>
</defs>
</svg>;

export const ExternalLink = ({text, href}) => <a href={href} rel="noopener noreferrer">
    {text}
  </a>;

<CardGroup cols={1}>
  <Card title="Get the Augment Extension" href="https://github.com/augmentcode/augment.vim" icon={<NeoVimLogo />} horizontal>
    View Augment for Vim and Neovim on GitHub
  </Card>
</CardGroup>

## About Installation

Installing <ExternalLink text="Augment for Vim and Neovim" href="https://github.com/augmentcode/augment.vim" /> is easy and will take you less than a minute. You can install the extension manually or you can use your favorite plugin manager.

## Prerequisites

Augment for Vim and Neovim requires a compatible version of Vim or Neovim, and Node.js:

| Dependency                                                                                     | Minimum version |
| :--------------------------------------------------------------------------------------------- | :-------------- |
| [Vim](https://github.com/vim/vim?tab=readme-ov-file#installation)                              | 9.1.0           |
| [Neovim](https://github.com/neovim/neovim/tree/master?tab=readme-ov-file#install-from-package) | 0.10.0          |
| [Node.js](https://nodejs.org/en/download/package-manager/all)                                  | 22.0.0          |

## 1. Install the extension

<Tabs>
  <Tab title="Neovim">
    ### Manual Installation

    ```sh
    git clone https://github.com/augmentcode/augment.vim.git ~/.config/nvim/pack/augment/start/augment.vim
    ```

    ### Using Lazy.nvim

    Add the following to your `init.lua` file, then run `:Lazy sync` in Neovim. See more details about using [Lazy.nvim on GitHub](https://github.com/folke/lazy.nvim).

    ```lua
    require('lazy').setup({
      -- Your other plugins here
      'augmentcode/augment.vim',
    })
    ```
  </Tab>

  <Tab title="Vim">
    ### Manual Installation

    ```sh
    git clone https://github.com/augmentcode/augment.vim.git ~/.vim/pack/augment/start/augment.vim
    ```

    ### Using Vim Plug

    Add the following to your `.vimrc` file, then run `:PlugInstall` in Vim. See more details about using [Vim Plug on GitHub](https://github.com/junegunn/vim-plug).

    ```vim
    call plug#begin()

    " Your other plugins here
    Plug 'augmentcode/augment.vim'

    call plug#end()
    ```
  </Tab>
</Tabs>

## 2. Configure your workspace context

Add your project root to your workspace context by setting `g:augment_workspace_folders` in your `.vimrc` or `init.lua` file before the plugin is loaded. For example:

```vim
" Add to your .vimrc
let g:augment_workspace_folders = ['/path/to/project']

" Add to your init.lua
vim.g.augment_workspace_folders = {'/path/to/project'}
```

Augment's Context Engine provides the best suggestions when it has access to your project's codebase and any related repositories. See more details in
[Configure additional workspace context](/vim/setup-augment/workspace-context-vim).

## 3. Sign-in to Augment

Open Vim or Neovim and sign-in to Augment with the following command:

```vim
:Augment signin
```

<Next>
  * [Using Chat with Vim and Neovim](/vim/using-augment/vim-chat)
  * [Using Completions with Vim and Neovim](/vim/using-augment/vim-completions)
  * [Configure keyboard shortcuts](/vim/setup-augment/vim-keyboard-shortcuts)
</Next>


# Commands and shortcuts for Vim and Neovim
Source: https://docs.augmentcode.com/vim/setup-augment/vim-keyboard-shortcuts

Augment flexibly integrates with your editor to provide keyboard shortcuts for common actions. Customize your keymappings to quickly accept suggestions and chat with Augment.

export const Command = ({text}) => <span className="font-bold">{text}</span>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

## All available commands

| Command                                         | Action                                      |
| :---------------------------------------------- | :------------------------------------------ |
| <Keyboard shortcut=":Augment enable" />         | Globally enable suggestions (on by default) |
| <Keyboard shortcut=":Augment disable" />        | Globally disable suggestions                |
| <Keyboard shortcut=":Augment chat <message>" /> | Send a chat message to Augment              |
| <Keyboard shortcut=":Augment chat-new" />       | Start a new chat conversation               |
| <Keyboard shortcut=":Augment chat-toggle" />    | Toggle the chat panel visibility            |
| <Keyboard shortcut=":Augment signin" />         | Start the sign in flow                      |
| <Keyboard shortcut=":Augment signout" />        | Sign out of Augment                         |
| <Keyboard shortcut=":Augment status" />         | View the current status of the plugin       |
| <Keyboard shortcut=":Augment log" />            | View the plugin log                         |

## Creating custom shortcuts

You can create custom shortcuts for any of the above commands by adding mappings to your `.vimrc` or `init.lua` file. For example, to create a shortcut for the :Augment chat\* commands, you can add the following mappings:

```vim
" Send a chat message in normal and visual mode
nnoremap <leader>ac :Augment chat<CR>
vnoremap <leader>ac :Augment chat<CR>

" Start a new chat conversation
nnoremap <leader>an :Augment chat-new<CR>

" Toggle the chat panel visibility
nnoremap <leader>at :Augment chat-toggle<CR>
```

## Customizing accepting a completion suggestion

By default <Keyboard shortcut="Tab" /> is used to accept a suggestion. If you want to use a key other than <Keyboard shortcut="Tab" /> to accept a suggestion, create a mapping that calls `augment#Accept()`. The function takes an optional arugment used to specify the fallback text to insert if no suggestion is available.

```vim
" Use Ctrl-Y to accept a suggestion
inoremap <c-y> <cmd>call augment#Accept()<cr>

" Use enter to accept a suggestion, falling back to a newline if no suggestion
" is available
inoremap <cr> <cmd>call augment#Accept("\n")<cr>
```

You can disable the default <Keyboard shortcut="Tab" /> mapping by setting `g:augment_disable_tab_mapping = v:true` before the plugin is loaded.


# Add context to your workspace
Source: https://docs.augmentcode.com/vim/setup-augment/workspace-context-vim

You can add additional context to your workspace–such as additional repositories and folders–to give Augment a full view of your system.

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Availability = ({tags}) => {
  const tagTypes = {
    invite: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    beta: {
      styles: "border border-zinc-500/20 bg-zinc-50/50 dark:border-zinc-500/30 dark:bg-zinc-500/10 text-zinc-900 dark:text-zinc-200"
    },
    vscode: {
      styles: "border border-sky-500/20 bg-sky-50/50 dark:border-sky-500/30 dark:bg-sky-500/10 text-sky-900 dark:text-sky-200"
    },
    jetbrains: {
      styles: "border border-amber-500/20 bg-amber-50/50 dark:border-amber-500/30 dark:bg-amber-500/10 text-amber-900 dark:text-amber-200"
    },
    vim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    neovim: {
      styles: "bg-gray-700 text-white dark:border-gray-50/10"
    },
    default: {
      styles: "bg-gray-200"
    }
  };
  return <div className="flex items-center space-x-2 border-b pb-4 border-gray-200 dark:border-white/10">
      <span className="text-sm font-medium">Availability</span>
      {tags.map(tag => {
    const tagType = tagTypes[tag] || tagTypes.default;
    return <div key={tag} className={`px-2 py-0.5 rounded-md text-xs font-medium ${tagType.styles}`}>
            {tag}
          </div>;
  })}
    </div>;
};

<Availability tags={["vim","neovim"]} />

## About Workspace Context

Augment is powered by its deep understanding of your code. You'll need to configure your project's source in your workspace context to get full codebase understanding in your chats and suggestions.

Sometimes important parts of your system exist outside of the current project. For example, you may have seperate frontend and backend repositories or have many services across multiple repositories. Adding additional codebases to your workspace context will improve the code suggestions and chat responses from Augment.

## Add context to your workspace

<Note>
  Be sure to set `g:augment_workspace_folders` before the Augment plugin is loaded.
</Note>

To add context to your workspace, in your `.vimrc` set `g:augment_workspace_folders` to a list of paths to the folders you want to add to your workspace context. For example:

```vim
let g:augment_workspace_folders = ['/path/to/folder', '~/path/to/another/folder']
```

You may want to ignore specific folders, like `node_modules`, see [Ignoring files with .augmentignore](/setup-augment/workspace-indexing#ignoring-files-with-augmentignore) for more details.

After adding a workspace folder and restarting Vim, the output of the <Keyboard shortcut=":Augment status" /> command will include the syncing progress for the added folder.


# Index your workspace
Source: https://docs.augmentcode.com/vim/setup-augment/workspace-indexing

When your workspace is indexed, Augment can provide tailored code suggestions and answers based on your unique codebase, best practices, coding patterns, and preferences. You can always control what files are indexed.

## About indexing your workspace

When you open a workspace with Augment enabled, your codebase will be automatically uploaded to Augment's secure cloud. You can control what files get indexed using `.gitignore` and `.augmentignore` files. Indexing usually takes less than a minute but can take longer depending on the size of your codebase.

## Security and privacy

Augment stores your code securely and privately to enable our powerful context engine. We ensure code privacy through a proof-of-possession API and maintain strict internal data minimization principles. [Read more about our security](https://www.augmentcode.com/security).

## What gets indexed

Augment will index all the files in your workspace, except for the files that match patterns in your `.gitignore` file and the `.augmentignore` file.

## Ignoring files with .augmentignore

The `.augmentignore` file is a list of file patterns that Augment will ignore when indexing your workspace. Create an `.augmentignore` file in the root of your workspace. You can use any glob pattern that is supported by the [gitignore](https://git-scm.com/docs/gitignore) file.

## Including files that are .gitignored

If you have a file or directory in your `.gitignore` that you want to indexed, you can add it to your `.augmentignore` file using the `!` prefix.

For example, you may want your `node_modules` indexed to provide Augment with context about the dependencies in their project, but it is typically included in their `.gitignore`. Add `!node_modules` to your `.augmentignore` file.

<CodeGroup>
  ```bash .augmentignore
  # Include .gitignore excluded files with ! prefix
  !node_modules

  # Exclude other files with .gitignore syntax
  data/test.json
  ```

  ```bash .gitignore
  # Exclude dependencies
  node_modules

  # Exclude secrets
  .env

  # Exclude build artifacts
  out
  build
  ```
</CodeGroup>


# Chat
Source: https://docs.augmentcode.com/vim/using-augment/vim-chat

Use Chat to explore your codebase, quickly get up to speed on unfamiliar code, and get help working through a technical problem.

export const Next = ({children}) => <div className="border-t border-b pb-8 border-gray dark:border-white/10">
    <h3>Next steps</h3>
    {children}
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## Using chat

Chat is a new way to work with your codebase using natural language. Use Chat to explore your codebase, quickly get up to speed on unfamiliar code, and get help working through a technical problem.

| Command                                         | Action                           |
| :---------------------------------------------- | :------------------------------- |
| <Keyboard shortcut=":Augment chat <message>" /> | Send a chat message to Augment   |
| <Keyboard shortcut=":Augment chat-new" />       | Start a new chat conversation    |
| <Keyboard shortcut=":Augment chat-toggle" />    | Toggle the chat panel visibility |

### Sending a message

You can send a message to Chat using the <Keyboard shortcut=":Augment chat" /> command. You can send your message as an optional argument to the command or enter it into the command-line when prompted. Each new message will continue the current conversation which will be used as context for your next message.

**Focusing on selected text**

If you have text selected in `visual mode`, Augment will automatically include it in your message. This is useful for asking questions about specific code or requesting changes to the selected code.

### Starting a new conversation

You can start a new conversation by using the <Keyboard shortcut=":Augment chat-new" /> command.

<Next>
  * [Using Completions](/vim/using-augment/vim-completions)
  * [Configure keyboard shortcuts](/vim/setup-augment/vim-keyboard-shortcuts)
</Next>


# Completions
Source: https://docs.augmentcode.com/vim/using-augment/vim-completions

Use code completions to get more done. Augment’s radical context awareness means more relevant suggestions, fewer hallucinations, and less time hunting down documentation.

export const Next = ({children}) => <div className="border-t border-b pb-8 border-gray dark:border-white/10">
    <h3>Next steps</h3>
    {children}
  </div>;

export const Keyboard = ({shortcut}) => <span className="inline-block border border-gray-200 bg-gray-50 dark:border-white/10 dark:bg-gray-800 rounded-md text-xs text-gray font-bold px-1 py-0.5">
    {shortcut}
  </span>;

export const Command = ({text}) => <span className="font-bold">{text}</span>;

## Using completions

Augment’s code completions integrates with Vim and Neovim to give you autocomplete-like suggestions as you type. Completions are enable by default and you can use <Keyboard shortcut="Tab" /> to accept a suggestion.

| Command                                  | Action                                      |
| :--------------------------------------- | :------------------------------------------ |
| <Keyboard shortcut="Tab" />              | Accept the current suggestion               |
| <Keyboard shortcut=":Augment enable" />  | Globally enable suggestions (on by default) |
| <Keyboard shortcut=":Augment disable" /> | Globally disable suggestions                |

### Customizing accepting a suggestion

If you want to use a key other than <Keyboard shortcut="Tab" /> to accept a suggestion, create a mapping that calls `augment#Accept()`. The function takes an optional arugment used to specify the fallback text to insert if no suggestion is available.

```vim
" Use Ctrl-Y to accept a suggestion
inoremap <c-y> <cmd>call augment#Accept()<cr>

" Use enter to accept a suggestion, falling back to a newline if no suggestion
" is available
inoremap <cr> <cmd>call augment#Accept("\n")<cr>
```

You can disable the default <Keyboard shortcut="Tab" /> mapping by setting `g:augment_disable_tab_mapping = v:true` before the plugin is loaded.

<Next>
  * [Using Chat](/vim/using-augment/vim-chat)
  * [Configure keyboard shortcuts](/vim/setup-augment/vim-keyboard-shortcuts)
</Next>