forge-studio

Web UI for ForgeEngine. FastAPI backend with a React frontend -- chat with Qwen3.6 reasoning models, ingest repos, toggle thinking mode, view token budget.

Install

pip install -e ".[dev]"
cd frontend && npm install && npm run build && cd ..

Run

# Set your inference backend
export FORGE_MODEL=Qwen3.6-27B
export FORGE_BASE_URL=http://localhost:8000/v1

# Start the server (binds to 127.0.0.1 by default)
forge-studio --port 8400

Open http://localhost:8400 in your browser.

Development mode

Run backend and frontend separately for hot reloading:

# Terminal 1: backend with auto-reload
forge-studio --port 8400 --dev

# Terminal 2: frontend dev server (proxies API to backend)
cd frontend && npm run dev

The Vite dev server runs on port 5173 and proxies /api requests to the backend on port 8400.

Configuration

Environment variables:

API

Tests

pytest -x -q

License

Apache 2.0