antigravity-sdk-python
Python library for building AI agents based on Google Antigravity.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 2.0k
- Source
- mcp-github
Overview
The Google Antigravity SDK is a Python library for building AI agents powered by Antigravity and Gemini. It provides a secure, scalable, and stateful infrastructure layer that abstracts the agent loop, allowing you to focus on agent functionality rather than its execution mechanics. With simple configuration and API calls, developers can quickly create powerful AI agents. Ideal for applications requiring advanced AI capabilities.
Capabilities
- ▪Supports multimodal input (text, image, video, etc.)
- ▪Real-time streaming response output
- ▪Tool invocation interception and handling
- ▪Streaming transmission of internal model inference
Use cases
Setup
pip install google-antigravity
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with this SDK?
Run the example scripts in the examples directory after installation.
Do I need additional binary files?
No, required binaries are automatically included during installation.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.