Antigravity OpenAI-Compatible Proxy

A small FastAPI wrapper that accepts OpenAI-compatible requests and invokes the local agy CLI. A chat request passes its requested model to agy --model <model> --prompt <prompt>. /v1/models runs agy models and exposes the returned model IDs. Antigravity CLI handles sign-in; model names are passed through unchanged.

Run on Termux (Android)

The agy command must already be installed, available in Termux's PATH, and signed in. Install the proxy from PyPI:

pkg update
pkg install python
python -m pip install --upgrade antigravity-proxy
antigravity-proxy --web

Then open http://127.0.0.1:8091/index.html in a browser. The UI gets the model list from agy models and sends chat requests through the same local proxy. The --web mode binds only to 127.0.0.1:8091. To run the API without the UI, start antigravity-proxy; it listens on port 8000 by default.

To configure the CLI executable or API port, create a .env file in the directory where you start the command. Defaults are AGY_EXECUTABLE=agy and PROXY_PORT=8000:

printf 'AGY_EXECUTABLE=agy\nPROXY_PORT=8000\n' > .env

To run from an unpacked source checkout instead, install its dependencies with python -m pip install . and start it with python main.py --web.

Test the proxy:

curl http://127.0.0.1:8000/health
curl http://127.0.0.1:8000/v1/models
curl -N http://127.0.0.1:8000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"YOUR_MODEL","messages":[{"role":"user","content":"Hello"}],"stream":true}'

/health runs agy models and returns HTTP 200 if the command succeeds, or 503 if it cannot start or returns an error. Chat requests execute agy --model <model> --prompt <prompt> without shell interpolation. Streaming requests are returned as SSE while stdout is produced by the CLI.