Google's Antigravity SDK now supports local agentic workflows with initial support for Gemma 4 26B A4B using Google AI Edge's LiteRT, enabling fully offline agentic assistance that efficiently uses local GPU and RAM. Developers can also use the LocalOpenAIAgentConfig to connect any OpenAI-compatible local server such as Ollama, LM Studio, or vLLM without changing orchestration or workflows. Google recommends a machine with >24GB VRAM or unified memory for the Gemma 4 26B workflow.
Read the full story on developers.googleblog.com
What to doTry local agentic workflows with the Antigravity SDK by following the README instructions, using a machine with >24GB VRAM or unified memory for Gemma 4 26B A4B via LiteRT, or connect your own OpenAI…
- Provider