🐰 CodeBunny

AI-Powered Code Reviews for GitHub Pull Requests

Features • Tech Stack • Getting Started • Environment • Contributing

---

✨ Features

• 🤖 AI-Powered Reviews - Automatically generate intelligent code reviews for your pull requests using Google's Gemini AI
• 🔗 GitHub Integration - Seamlessly connect your repositories with one-click OAuth authentication
• 📊 Dashboard Analytics - Track your coding activity, commits, PRs, and AI reviews with beautiful visualizations
• 🎯 RAG-Enhanced Context - Retrieval-Augmented Generation using Pinecone for codebase-aware reviews
• ⚡ Real-time Processing - Background job processing with Inngest for non-blocking review generation
• 📈 Contribution Graphs - Visualize your coding frequency over time
• 🌙 Modern UI - Beautiful, responsive interface built with Shadcn/UI and TailwindCSS

🛠️ Tech Stack

Category	Technology
Framework	Next.js 16 (App Router)
Language	TypeScript
Styling	TailwindCSS 4 + Shadcn/UI
Database	PostgreSQL + Prisma ORM
Authentication	Better Auth (GitHub OAuth)
AI	Google Gemini via AI SDK
Vector Store	Pinecone
Background Jobs	Inngest
Data Fetching	TanStack Query
Package Manager	Bun

📋 Prerequisites

Before you begin, ensure you have the following installed:

• Node.js (v18 or higher)
• Bun (recommended) or npm/yarn/pnpm
• PostgreSQL database
• Git

You'll also need accounts for:

• GitHub (for OAuth app)
• Google AI Studio (for Gemini API key)
• Pinecone (for vector storage)
• Inngest (for background jobs)

🚀 Getting Started

1. Clone the Repository

git clone https://github.com/yourusername/codebunny.git
cd codebunny

2. Install Dependencies

bun install
# or
npm install

3. Set Up Environment Variables

Copy the example environment file and fill in your values:

cp .env.example .env

See Environment Variables for detailed configuration.

4. Set Up the Database

# Generate Prisma client
bun prisma generate

# Run migrations
bun prisma migrate dev

5. Start the Development Server

bun run dev

6. Start Inngest Dev Server (in a separate terminal)

npx inngest-cli@latest dev

7. (Optional) Expose Local Server for Webhooks

For GitHub webhooks during development, use ngrok:

ngrok http 3000

Open http://localhost:3000 to see the application.

⚙️ Environment Variables

Create a .env file in the root directory with the following variables:

# Database
DATABASE_URL="postgresql://user:password@localhost:5432/codebunny"

# Better Auth
BETTER_AUTH_SECRET="your-secret-key-here"
BETTER_AUTH_URL="http://localhost:3000"

# GitHub OAuth
GITHUB_CLIENT_ID="your-github-client-id"
GITHUB_CLIENT_SECRET="your-github-client-secret"

# Application URL (use ngrok URL for webhooks during development)
NEXT_PUBLIC_APP_BASE_URL="http://localhost:3000"

# Google AI (Gemini)
GOOGLE_GENERATIVE_AI_API_KEY="your-gemini-api-key"

# Pinecone (Vector Store)
PINECONE_DB="your-pinecone-db-name"
PINECONE_DB_API_KEY="your-pinecone-api-key"

Getting API Keys

Service	How to Get
GitHub OAuth	Create OAuth App → Set callback URL to http://localhost:3000/api/auth/callback/github
Google Gemini	Google AI Studio → Create API key
Pinecone	Pinecone Console → Create account → Get API key and database name

📁 Project Structure

codebunny/
├── app/                    # Next.js App Router pages
│   ├── (auth)/            # Authentication routes
│   ├── api/               # API routes & webhooks
│   └── dashboard/         # Dashboard pages
├── components/            # Reusable UI components
│   └── ui/               # Shadcn/UI components
├── hooks/                 # Custom React hooks
├── inngest/              # Inngest background functions
│   └── function/         # Review generation logic
├── lib/                   # Utility functions & configs
├── module/               # Feature modules
│   ├── ai/              # AI review logic
│   ├── auth/            # Authentication utilities
│   ├── dashboard/       # Dashboard actions
│   ├── github/          # GitHub API integration
│   ├── repository/      # Repository management
│   ├── review/          # Review management
│   └── settings/        # User settings
├── prisma/               # Database schema & migrations
└── public/               # Static assets

🔄 How It Works

1. Connect Repository - User authenticates with GitHub and connects their repositories
2. Webhook Setup - CodeBunny registers a webhook on the connected repository
3. PR Event - When a pull request is opened or updated, GitHub sends a webhook
4. AI Processing - Inngest picks up the event and:
   • Fetches the PR diff from GitHub
   • Retrieves relevant context from Pinecone (RAG)
   • Generates a comprehensive review using Gemini AI
5. Post Review - The AI review is posted as a comment on the PR
6. Dashboard - User can view all reviews and analytics in the dashboard

🤝 Contributing

Contributions are welcome! Please read our Contributing Guide and Code of Conduct before submitting a pull request.

🔒 Security

For security concerns, please review our Security Policy.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

Made with ❤️ by Paras Patankar