Google Antigravity SDK Adds Local Model Support for Greater Token Efficiency and Code Privacy

InfoQ Homepage News Google Antigravity SDK Adds Local Model Support for Greater Token Efficiency and Code Privacy Google has introduced support for local models in the Antigravity SDK, enabling developers to build and execute agentic workflows directly on their own machines, while retaining the flexibility to mix in cloud-based models for higher-level tasks. This approach gives developers greater control over data privacy, inference costs, network dependencies, and computational workload distribution. One of the most compelling capabilities of the Antigravity SDK is hybrid agent orchestration, which adapts Google's proposed Architect-Builder pattern to a mixed cloud-local compute environment. According to the Architect-Builder pattern, one primary, high-context AI agent, the architect, holds the macro-level system view, including dependencies, architectural guardrails, and detailed specifications or implementation plans.