Antigravity SDK now supports local execution with Gemma 4 and LiteRT

The Antigravity SDK now supports local execution with Gemma 4 and LiteRT, so agents can run entirely on a local machine. Google Gemma says this setup has zero token costs, total data privacy, and offline reliability.

The SDK also supports OpenAI-compatible endpoints, so Ollama, llama.cpp, vLLM, and other tools can serve Gemma. The install command is pip install google-antigravity litert-lm. Details are on the Google Developers Blog: local AI models in the Antigravity SDK.