AI-powered code editor. Bring your own API keys.

Demo · Quick Start · Architecture · Contributing

---

Lumnicode is an online code editor with built-in AI assistance. Unlike other AI coding tools, you connect your own API keys from any supported provider -- no subscriptions, no per-seat pricing, no vendor lock-in.

Key highlights:

• Multi-provider AI -- OpenAI, Anthropic, Google Gemini, Groq, Together, Fireworks, Cohere
• BYOK (Bring Your Own Keys) -- use your existing API keys, pay only for what you use
• Monaco Editor -- VS Code-level editing with syntax highlighting, intellisense, and themes
• AI Command Palette -- Cmd+K for explain, refactor, complete, find bugs, generate tests
• Streaming responses -- token-by-token AI output via Server-Sent Events
• LangGraph orchestration -- AI project generation with plan-config-generate-finalize pipeline
• S3 file storage -- MinIO in development, any S3-compatible service in production
• Real-time updates -- WebSocket-driven progress for AI generation

Screenshots coming soon. Run locally to see the full experience.

• Docker Desktop (for Postgres + MinIO)
• Node.js 20+
• Python 3.11+
• uv (Python package manager)

git clone https://github.com/martian56/lumnicode.git
cd lumnicode
docker-compose -f docker-compose.dev.yml up -d

This starts PostgreSQL (port 5432) and MinIO (ports 9000/9001).

cd backend
cp .env.example .env   # Edit with your Clerk keys
uv sync
uv run alembic upgrade head
uv run uvicorn main:app --reload --host 0.0.0.0 --port 8000

cd frontend
cp .env.example .env   # Edit with your Clerk publishable key
npm install
npm run dev

Visit http://localhost:5173, sign in with Clerk, add your AI API key in Settings > API Keys, and start coding.

                         +------------------+
                         |    React SPA     |
                         |   (Vite + TS)    |
                         +--------+---------+
                                  |
                    REST / SSE / WebSocket
                                  |
                         +--------+---------+
                         |    FastAPI       |
                         |   (Python)       |
                         +--------+---------+
                                  |
              +-------------------+-------------------+
              |                   |                   |
     +--------+------+   +-------+-------+   +-------+-------+
     |   PostgreSQL  |   |  MinIO (S3)   |   |  AI Providers |
     |  (metadata)   |   | (file content)|   | (LangChain)   |
     +---------------+   +---------------+   +---------------+

User Request
     |
     v
LLM Provider Factory (llm_provider.py)
     |
     +-- ChatOpenAI        (OpenAI, Together, Fireworks, Groq)
     +-- ChatAnthropic     (Claude)
     +-- ChatGoogleGenAI   (Gemini)
     |
     v
LangGraph State Machine (generation_graph.py)
     |
     +-- plan_node       --> Analyze requirements, plan file structure
     +-- config_node     --> Generate package.json, tsconfig, etc.
     +-- generate_node   --> Generate source files, write to S3
     +-- finalize_node   --> Update project, mark complete
     |
     v
WebSocket Progress Updates --> Frontend

Backend (backend/.env):

Frontend (frontend/.env):

Once the backend is running, access the interactive API docs:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

# Backend
cd backend
uv run black .              # Format
uv run ruff check .         # Lint
uv run pytest               # Test

# Frontend
cd frontend
npm run lint                 # Lint
npm run build                # Type check + build

cd backend
uv run alembic revision --autogenerate -m "describe change"
uv run alembic upgrade head

Access the MinIO web console at http://localhost:9001 (user: lumnicode, password: lumnicode123) to browse stored files.

# Set required environment variables
export POSTGRES_PASSWORD=your_secure_password
export S3_ACCESS_KEY=your_s3_key
export S3_SECRET_KEY=your_s3_secret

# Start all services
docker-compose up --build -d

Deploy the backend and frontend separately to any platform that supports Python/Node.js. Point S3_ENDPOINT_URL to your S3-compatible storage (AWS S3, DigitalOcean Spaces, Cloudflare R2, etc).

• Real-time collaboration (multi-user editing)
• Git integration (clone, commit, push from editor)
• Terminal emulator
• Plugin system
• Self-hosted deployment guide
• Mobile responsive editor

Contributions are welcome! See CONTRIBUTING.md for guidelines.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes
4. Push to the branch
5. Open a Pull Request

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