Google Antigravity SDK
Google Antigravity SDK is a Python library that lets developers build AI agents powered by Gemini and Antigravity without managing the agent loop.
What it is good for
- Building an AI agent that calls custom Python functions as tools
- Connecting an agent to external MCP servers for extra tools
- Streaming agent responses into a console or user interface
- Running an AI agent offline on a local model
At a glance
- Who it is for
- Setup
- Requires programming
Level 5 of 5. You need to write code to use it.
- Cost
- Free and open source
- Type
- Framework or SDK
- Tasks
- Works with
- Gemini, Google Antigravity, Gemini Enterprise Agent Platform, LiteRT-LM, Gemma 4, MCP servers
Momentum
- Rank this week
- Not ranked (last #50, week 41, 2026)
- Best rank
- #44 week 40, 2026
- GitHub stars
- 3,916
GitHub numbers as of Nov 2, 2026. Updated weekly.
Ranking history
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is Google Antigravity SDK free?
- Yes. It is free and open source (Apache-2.0 license).
- Do I need to know how to code to use Google Antigravity SDK?
- Yes. You need to write code to use it.
- What does Google Antigravity SDK work with?
- According to its own documentation, it works with Gemini, Google Antigravity, Gemini Enterprise Agent Platform, LiteRT-LM, Gemma 4, and MCP servers.
- What is Google Antigravity SDK good for?
- Building an AI agent that calls custom Python functions as tools, connecting an agent to external MCP servers for extra tools, streaming agent responses into a console or user interface, and running an AI agent offline on a local model.
Similar agents to Google Antigravity SDK
- AgentScope
AgentScope is a framework that helps developers build and run AI agents they can monitor and trust.
- Composio
Composio is a developer SDK that gives AI agents pre-authenticated access to 1000+ apps for developers building agents.
- FastMCP
FastMCP is a Python framework that helps developers build MCP servers and clients, connectors that let AI apps use other tools and data.
- Trigger.dev
Trigger.dev is a TypeScript platform that runs long AI agent tasks without timeouts for developers building agents and workflows.
- agent-desktop
agent-desktop is a command-line tool that lets AI agents read and operate desktop apps on macOS, Windows and Linux for developers.
- Swarms
Swarms is a Python framework that lets developers build teams of AI agents that split up and complete multi-step work.