Back to directory

Google Antigravity SDK

A Python SDK for building AI agents powered by Google's Antigravity platform and Gemini models, with a stateful runtime that handles the agent loop.

Google Antigravity SDK

The Google Antigravity SDK is a Python SDK for building AI agents powered by Antigravity and Gemini. It provides a secure, scalable, stateful infrastructure layer that runs the agentic loop, so applications built on it focus on what the agent does rather than how it executes.

Installation is through PyPI, which ships a platform-specific wheel containing a compiled runtime binary; cloning the repository alone does not provide a runnable SDK. Agents can authenticate to the Gemini Enterprise Agent Platform (formerly Vertex AI) either with a plain API key in Express Mode, for setups without a Google Cloud project, or with a project and location in Standard Mode, which uses Application Default Credentials.

Configuration can be supplied through code or through environment variables such as GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.