# GitHub Integration
Deploy your AI as a GitHub App that responds to issues, pull requests, and discussions with full repository context.
---
Deploy your Chipp AI as a GitHub App. Users @mention your bot in issues, pull requests, and discussions to get AI-powered responses with full repository context -- perfect for code review, issue triage, security auditing, and documentation.
> **Note:** GitHub integration requires a Builder plan or higher.
> href="https://build.chipp.ai/plans"
> target="_blank"
> rel="noopener noreferrer"
>
> >
> Upgrade to Builder →
>
## What the GitHub Bot Can Do
| Capability | Description |
|-----------|-------------|
| **Read repository files** | Access source code, configs, and documentation |
| **Review pull requests** | Analyze diffs and changed files with context |
| **Search code** | Find patterns, functions, and references across the repo |
| **Triage issues** | Categorize, label, and respond to new issues |
| **Post comments** | Respond in issues, PRs, and discussions |
| **Add labels** | Automatically label issues and PRs for organization |
## Getting Started
GitHub uses a streamlined one-click manifest flow -- no manual OAuth configuration needed.
**1.**
Deploy to GitHub
Go to your app's **Share** page → **Deploy** tab → **Deploy on GitHub** card. Click **Add Deployment**.
You'll be redirected to GitHub to create a GitHub App from a pre-configured manifest. Click **Create GitHub App** and confirm.
**2.**
Install to Repositories
After creation, GitHub provides an install link. Select which repositories should have access to the bot. You can install it on specific repos or your entire organization.
**3.**
Start Using
Your bot is now active. @mention its slug in any issue, PR, or discussion to get a response. The slug is displayed in the integration status panel.
```
@my-app-chipp-ai Can you review this PR for security issues?
```
## How It Works
When someone @mentions your bot:
1. GitHub sends a webhook to Chipp with the comment context
2. Your bot reads the issue/PR details, including title, description, labels, and diffs
3. Repository tools are registered so the bot can read files, search code, and review changes
4. The AI generates a response using your app's system prompt and knowledge base
5. The response is posted as a GitHub comment in Markdown format
The bot shows a thinking indicator (eyes emoji) while processing and a rocket emoji when done.
## Supported Events
| Event | Trigger | Bot Responds In |
|-------|---------|-----------------|
| **Issue comment** | @mention in an issue | Same issue thread |
| **PR comment** | @mention on a pull request | Same PR thread |
| **PR review comment** | @mention on an inline code comment | Same review thread |
| **Discussion comment** | @mention in a GitHub Discussion | Same discussion |
| **New issue** | Issue opened (if auto-respond enabled) | New comment on the issue |
The bot only responds to human-created events. Comments from other bots are ignored to prevent loops.
## Repository Tools
When your bot responds, it has access to these tools for understanding your codebase:
| Tool | What It Does |
|------|--------------|
| **Get file contents** | Read any file by path (source code, configs, docs) |
| **Get PR diff** | View the complete unified diff of a pull request |
| **Get PR files** | List changed files with addition/deletion counts |
| **Search code** | Find patterns and references across the repository |
| **List issues** | Search and filter issues by state, labels, or assignee |
| **Get comment thread** | Read the full conversation history |
| **Create comment** | Post follow-up comments for multi-step responses |
| **Add label** | Apply labels for automated triage |
| **Add reaction** | React to comments with emoji |
## Configuration
### Auto-Respond to New Issues
By default, the bot only responds when @mentioned. You can enable **auto-respond** to have the bot automatically comment on every newly opened issue -- useful for support repos and issue triage workflows.
Toggle this in your app's GitHub settings under **Share & Deploy**.
## Pre-Built Templates
Chipp provides GitHub-optimized templates to get started quickly:
| Template | Purpose |
|----------|---------|
| **Code Reviewer** | In-depth PR code review |
| **Security Reviewer** | OWASP/CWE-focused security audits |
| **Issue Triage** | Categorize issues and suggest labels |
| **Docs Assistant** | Explain codebase and generate documentation |
| **Release Notes Generator** | Summarize merged PRs into release notes |
Each template comes with an optimized system prompt and suggested starting messages.
## Permissions
The GitHub App requests these permissions during setup:
| Permission | Access Level | Why |
|-----------|-------------|-----|
| **Contents** | Read | Read repository files and code |
| **Issues** | Write | Post comments, add labels |
| **Pull Requests** | Write | Post comments, review diffs |
| **Discussions** | Write | Post in GitHub Discussions |
| **Metadata** | Read | Access repo names and public metadata |
The bot is read-only for code. It can post comments and labels but cannot modify code or merge pull requests.
## Rate Limits
| Resource | Limit |
|----------|-------|
| GitHub API requests | 5,000/hour per installation |
| Code search | 10 requests/minute |
| Comment length | 65,536 characters |
For typical usage (dozens of daily interactions), you won't hit these limits. Code search is the tightest constraint -- the bot uses it sparingly in high-volume scenarios.
## Billing
GitHub integration uses your standard LLM token billing. There's no separate per-message fee for GitHub interactions. GitHub API calls (reading files, searching code) are free and not metered.
## Troubleshooting
**Bot not responding?**
- Make sure you @mentioned the exact bot slug (shown in your GitHub settings)
- Verify the bot is installed on the repository in question
- Check that the webhook URL is active in your GitHub App settings
**Responses seem generic?**
- Add knowledge sources to your app for domain-specific context
- Customize the system prompt to focus on your use case (code review, triage, etc.)
- Use one of the pre-built templates as a starting point
**Rate limit errors?**
- Code search is limited to 10/minute. If your bot searches frequently, space out requests
- Consider using file reads instead of code search for known file paths
> **Note:** MCP server access requires a Builder plan or higher. See the [MCP Setup Guide](/docs/guides/mcp/setup) to get started.