NEWS · CODING · #1949
Google's Antigravity SDK adds local model support for hybrid cloud–local agent workflows
Google added support for local models to the Antigravity SDK, letting developers run agent 'builders' on-device while the higher‑context 'architect' can remain in the cloud. The initial implementation targets running Gemma 4 26B A4B via LiteRT, but the SDK also supports OpenAI‑compatible local inference servers (LocalOpenAIAgentConfig) such as Ollama, LM Studio, and vLLM; Google reports an example where ~97.2% of tokens were consumed locally and no source code was uploaded to the cloud.
KEY POINTS
- Google added support for local models to the Antigravity SDK, letting developers run agent 'builders' on-device while the higher‑context 'architect' can remain in the cloud.
- The initial implementation targets running Gemma 4 26B A4B via LiteRT, but the SDK also supports OpenAI‑compatible local inference servers (LocalOpenAIAgentConfig) such as Ollama, LM Studio, and vLLM; Google reports an example where ~97.2% of tokens were consumed locally and no source code was uploaded to the cloud.
- Enables hybrid architect/builder agent workflows that keep code‑intensive tasks on device, improving privacy and reducing cloud token use, though local hardware requirements may limit adoption.
WHY IT MATTERS
Enables hybrid architect/builder agent workflows that keep code‑intensive tasks on device, improving privacy and reducing cloud token use, though local hardware requirements may limit adoption.