Google Antigravity SDK 新增本地模型支持，提升 token 效率与代码隐私
原标题：Google Antigravity SDK Adds Local Model Support for Greater Token Efficiency and Code Privacy
AI 摘要
Google 在 Antigravity SDK 中新增本地模型支持，开发者可在本机运行智能体工作流，同时保留混合调用云端模型的能力，从而更好地控制数据隐私、推理成本和网络依赖。该 SDK 采用 Architect-Builder 模式：云端架构师负责规划，本地构建者执行代码修复、漏洞复现与回归测试等任务。演示中约 3400 个 token 仅 95 个用于云端规划，97.2% 在本地消耗，且源码未上传云端。初始实现基于 LiteRT 运行 Gemma 4 26B A4B，也支持 Ollama、LM Studio、vLLM 等 OpenAI 兼容本地推理服务。
正文节选
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