## Get started in minutes
Augment works with your favorite IDE and your favorite programming language. Download the extension, sign in, and get coding.
Get completions, chat, and instructions in your favorite open source editor.
Completions are available for all JetBrains IDEs, like WebStorm, PyCharm, and IntelliJ.
Get completions and chat in your favorite text editor.
You'll be redirected to authorize the integration with the appropriate service. After authorization, the integration will be available for use with Augment Agent.
## 
#### Adding user guidelines
You can add user guidelines by clicking 
## Installing Augment for JetBrains IDEs
in the side bar of your IDE. See more details in [Sign
In](/setup-augment/sign-in).
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, including any arguments and environment variables.
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.
## 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.
## 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 
### 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.
### 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.
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.
### 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 = () => 
## Accessing Chat
Access the Chat sidebar by clicking the Augment icon 
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 | 
## Using actions in Chat
To use a quick action, you an use a 
## 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
in the status bar at the bottom right corner of your IDE, then selecting in the status bar at the bottom right corner of your IDE, then selecting
Install Augment for Visual Studio Code
Install Augment for JetBrains IDEs, including WebStorm, PyCharm, and IntelliJ
Get completions and chat in your favorite text editor.
You'll be redirected to authorize the integration with the appropriate service. After authorization, the integration will be available for use with Augment Agent.
##
You can add user guidelines by clicking Context menu (@), starting an @-mention inside Chat, or clicking Settings > Rules and User Guidelines. User Guidelines will be applied to all future chats in all open editors.
### Adding from the Context menu (@) User Guidelines
1. Select User Guidelines
2. Enter your guidelines (see below for tips)
3. Click Save
4. Updating or removing user guidelines
### Adding from Settings > User Guidelines and Rules
1. In the top right corner, select the menu (⋯)
2. Select Settings
3. From the left menu in Augment Settings, select User Guidelines and Rules
4. Click + Create new rule file
5. Add your rule
6. Click Create
### Removing or modifying User Guidelines
You can update or remove your guidelines by clicking on the User Guidelines context chip. Update or remove your guidelines and click Save. Updating or removing user guidelines in any editor will modify them in all open editors.
## Working with Workspace Guidelines
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 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
### 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)
### 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)
## 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
## Tips for good Rules
* 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
## Importing Rules
**Augment** will automatically import rules if they are detected in the current workspace. Augment will look for markdown files, eg. files ending with `*.md` or `*.mdc`. You can also manually import rules inside of Settings > Import rules.
### 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.
## How are Rules different from Guidelines?
Guidelines and Rules differ in how they are stored and their scope of influence. Rules are defined by you and guide the AI to your specific preferences. Guidelines are
* **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.
* **Workspace Guidelines** stored within the repository under the `.augment-guidelines` file are a legacy set of rules that can be 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.
* **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.
## 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
# 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}) => 
### 2. Install Slack App
## Installing Augment for Visual Studio Code
in the side bar of your IDE. See more details in [Sign
In](/setup-augment/sign-in).
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, including any arguments and environment variables.
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.
## Configure in `settings.json`
Before you can use an integration in Agent, you'll need to configure the MCP server in in the status bar.
## Add context to your workspace
To add context to your workspace, click 
| Synced, or sync in progress |
| 
| Not synced |
| 
| 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.
{" "}
in the status bar at the bottom right corner of your editor, and select
`Show History` from the command menu.
{" "}
in the action bar on the left side of your editor.
{" "}
in the status bar at the bottom right corner of your editor, and select
`Show History` from the command menu.
## 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 
### 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.
### 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.
### 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.
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.
### 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 = () =>
## Accessing Chat
Access the Chat sidebar by clicking the Augment icon 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 |
## Using actions in Chat
To use a quick action, you an use a
## 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 in the status bar at the bottom right corner of your IDE, then selecting in the status bar at the bottom right corner of your IDE, then selecting 
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.
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 
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
(
1. **Editor Title Icon** (Top Right): Changes colors when next edits are available.
Click on the 
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
### Agent dashboard
You can view all of your remote agents in the Remote Agent dashboard by clicking the 
## 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
#### 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.
### 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.
### Connecting to a Remote Agent environment
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 
### 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 
## Adding Augment to Channels
Mention