A multi-LLM "AI Think Tank" where users bring their own API keys to facilitate three-way conversations between top-tier models.
- BYOK (Bring Your Own Key): Users manage their own API costs
- Zero-Persistence Security: API keys never stored on server
- Multi-Model Debates: Compare responses from different LLM architectures
- Free-Tier Optimization: Auto-detect models with free usage tiers
- Frontend: Next.js 16 (App Router) + Tailwind CSS
- Backend: FastAPI (Python) + LiteLLM
- Storage: LocalStorage for keys (no server-side storage)
- Node.js 18+
- Python 3.10+
- API keys for desired providers (OpenAI, Anthropic, Google, etc.)
# Frontend
cd frontend
npm install
npm run dev
# Backend
cd backend
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
uvicorn app.main:app --reload├── frontend/ # Next.js application
├── backend/ # FastAPI server
├── docs/ # Documentation
│ ├── roadmap.md # Development roadmap
│ └── DEPLOYMENT.md # Deployment guide
└── README.md
Ready to deploy your own instance? See docs/DEPLOYMENT.md for detailed instructions on deploying to Vercel (frontend) and Railway (backend).
Quick links:
- Frontend:
- Backend: Deploy on Railway
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
If you find this project helpful, consider:
MIT