> ## Documentation Index
> Fetch the complete documentation index at: https://composio-27-feat-docs-revamp.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# SWE Kit: PR Review Agent

> Build a PR Review agent with SWE Kit

## Overview

SWE Development Kit (swekit) is a powerful framework for building Software Engineering agents using Composio's tooling ecosystem. This example demonstrates how to build a Pull Request (PR) Review Agent using SWE Development Kit (swekit). The PR Review Agent uses Composio's tooling ecosystem to help automate and enhance the PR review process.

## Getting Started

<Steps>
  <Step title="Installation">
    Begin by installing the core packages:

    <CodeGroup>
      ```bash Installing SweKit
      pip install swekit composio-core
      ```
    </CodeGroup>

    For additional functionality, install packages for your preferred framework (e.g., LangChain):

    <CodeGroup>
      ```bash Installing LangChain and Composio LangChain Plugin
      pip install langchain composio-langchain
      ```
    </CodeGroup>
  </Step>

  <Step title="Connect your Github Account">
    To utilize Github Issues as a task source, link your Github account as follows:

    <Tabs>
      <Tab title="Composio CLI">
        <CodeGroup>
          ```bash Use Composio CLI
          composio add github
          ```
        </CodeGroup>
      </Tab>

      <Tab title="Locally using Github Auth Token">
        <CodeGroup>
          ```bash Use Github Auth Token
          export GITHUB_ACCESS_TOKEN=<your_token>
          ```
        </CodeGroup>
      </Tab>
    </Tabs>

    <Note>
      There are two ways to provide the GitHub access token for git clone:

      1. Set the environment variable `GITHUB_ACCESS_TOKEN='<git_access_token>'`.
      2. Use the GitHub account connected to your toolset entity. However, this method has limitations:
         * The agent won't be able to push or create PRs.
         * You need to set `export ALLOW_CLONE_WITHOUT_REPO='true'`.

      Option 1 is recommended for full functionality.
    </Note>
  </Step>

  <Step title="Create a New Agent">
    Generate your agent's scaffolding:

    <CodeGroup>
      ```bash Create a new Folder with basic PR Review agent code
      swekit scaffold pr_review -f langgraph -o pr_review_agent
      ```
    </CodeGroup>

    | Argument | Description                                   | Accepted Values          |
    | -------- | --------------------------------------------- | ------------------------ |
    | `-f`     | Specifies the framework to use                | `langgraph`              |
    | `-o`     | Sets the output directory for generated files | Any valid directory path |

    <Note>
      Scaffold support for other frameworks coming soon!
    </Note>

    This process will establish a new agent at `pr_review_agent` with essential files:

    * `main.py`: The main script to execute the agent
    * `agent.py`: The agent's core definition
    * `prompts.py`: Prompts to guide the agent's actions
    * `input.py`: A helper file to take inputs from the user
    * `tools.py`: A file to add custom tools to the agent
  </Step>

  <Step title="Start Docker Server">
    <Warning>
      To use Docker as the default workspace environment, ensure your Docker server is running
    </Warning>

    If you prefer to run the agent locally without Docker (**Unsafe**), modify the workspace configuration in `agent.py` by setting the `WorkspaceType.Docker()` to `WorkspaceType.Host()`.
  </Step>

  <Step title="Run the Agent">
    To activate the agent, proceed to its directory and execute:

    <CodeGroup>
      ```bash Run the agent
      cd pr_review_agent/agent
      python main.py
      ```
    </CodeGroup>

    You will be prompted to specify the repository and issue for the agent to address.
  </Step>
</Steps>