# Antigravity SDK now supports local execution with Gemma 4 and LiteRT

Agentic workflows can run entirely on a local machine through Gemma 4 and LiteRT. The SDK also supports OpenAI-compatible endpoints, including Ollama, llama.cpp, and vLLM.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T07:31:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/97d6001d044942a2a130046f.html

Content language: en
Localization state: sameLanguage

Source: Google Gemma · Published 9/23/2026, 14:01:19

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](https://developers.googleblog.com/introducing-support-for-local-ai-models-in-the-antigravity-sdk/).

Tags: Antigravity SDK, Gemma, LiteRT, Local AI

[View original post](https://x.com/googlegemma/status/2102864681589493924)