An intelligent multi-agent system that automatically generates comprehensive documentation for GitHub repositories using CrewAI's collaborative agent framework.
- Python 3.11+
- Node.js 18+
- OpenAI API key
-
Backend Setup
cd backend python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txt cp .env.example .env # Edit .env and add your OPENAI_API_KEY python main.py
-
Frontend Setup
cd frontend npm install npm run dev -
Usage
- Open http://localhost:3000
- Enter a GitHub repository URL
- Watch AI agents collaborate in real-time
- Download generated documentation
- Multi-Agent Collaboration: Five specialized AI agents working together
- Real-time Progress: Watch agents analyze, write, and review documentation
- Comprehensive Analysis: Deep code analysis and pattern recognition
- Professional Output: Export-ready markdown documentation
- Interactive UI: Beautiful visualization of the AI workflow
The system uses five specialized agents:
- Code Analyzer - Repository structure analysis
- API Documenter - API endpoint documentation
- README Writer - User-friendly documentation
- Example Creator - Usage examples and samples
- Editor - Quality review and polishing
Backend: CrewAI, LangChain, FastAPI, Python 3.11+
Frontend: Next.js 14, TypeScript, Tailwind CSS, Socket.io
- Development Guide - Architecture and setup details
- API Reference - Endpoint documentation
- Deployment Guide - Production deployment
This is a portfolio project demonstrating multi-agent AI systems. Feel free to explore the code and suggest improvements.
MIT License - see LICENSE file for details.