LibreAI / Agents IA / antigravity-sdk-python

// agents · google-antigravity/antigravity-sdk-python

antigravity-sdk-python

antigravity-sdk-python est un projet de agents IA open source, créé par google-antigravity (google-antigravity/antigravity-sdk-python sur GitHub). Il compte 3 664 étoiles sur GitHub et 1 456 forks, il est publié sous la licence Apache-2.0 et a été mis à jour pour la dernière fois sur GitHub le 7 octobre 2026.

Google's Python SDK for building AI agents on the Antigravity platform and Gemini models.

★ 3,7 k étoiles⑂ 1,5 k forksApache-2.0mis à jour oct. 2026

Voir sur GitHub ↗Official site ↗

▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.

// détails du projet

Détails du projet

Dépôt: google-antigravity/antigravity-sdk-python
Étoiles GitHub: 3 664
Forks: 1 456
Licence: Apache-2.0
Dernière mise à jour sur GitHub: 7 octobre 2026
Catégorie: Agents IA
Type de fiche: Guide d'installation complet
Site officiel: Official site

// fonctionnement

Comment ça marche

Clarify your goal
Decide the first concrete outcome you want from it, so you can pick the right example, template or mode instead of exploring everything at once.
Get the project
Clone the repository (or install the published package) and skim its README quick start for the requirements for your platform.
Install and configure
Run the documented install step and set any required configuration — such as provider keys, data sources or local services — before the first run.
Run your first task
Execute the smallest documented example end to end, confirm the output is what you expected, then adapt it to your real data or workflow.

// fonctionnalités

Pourquoi on l'adore

One-class agents

The Agent class handles lifecycle, tool wiring, hook registration and policy defaults behind an async context manager.

Streaming everywhere

Stream responses, reasoning/thinking deltas and strongly-typed ToolCall events without blocking.

Custom tools and MCP

Define custom tools and connect MCP servers to extend what agents can do.

Multimodal ingestion

Send mixed text and content objects — filesystem paths resolve automatically to document types.

Hooks, policies and triggers

Control agent behaviour with hooks and policies, and react to triggers.

Local models too

Run agents against locally imported LiteRT-LM models by pointing at the model path.

// lancez-le

Lancez-le vous-même

Clone the repository

Get the source so you can inspect, configure and run it locally.

git clone https://github.com/google-antigravity/antigravity-sdk-python.git
cd antigravity-sdk-python

Install the SDK
Install the package from PyPI.
```
pip install google-antigravity
```
Set your key and run the quickstart
Export a Gemini API key for express mode (or use ADC project/location for Vertex standard mode), then run the quickstart Agent example.
```
export GEMINI_API_KEY=your-key  # see README quickstart for the agent code
```

// cas d'usage

Ce que vous pouvez créer

Build a Gemini agent that streams its reasoning to your UI
Create a document-answering agent with multimodal file inputs
Wire MCP tools into a Google-ecosystem agent
Prototype an agent on the API, then move it to Vertex AI for production

// faq

Questions fréquentes

Who maintains antigravity-sdk-python?

It is maintained by google-antigravity on GitHub (google-antigravity/antigravity-sdk-python), where the source, issues and releases live.

Is it free to use?

Yes — it is free and open source under Apache-2.0, which permits use, modification and commercial redistribution, with licence/notice retention.

Does it need a paid API key?

Express mode uses a Gemini API key (usage is billed by Google); standard mode routes through a Google Cloud project with ADC, and local LiteRT-LM models avoid API calls.

How does it compare to Google's genai SDK used directly, or frameworks like LangGraph?

Compared with Google's genai SDK used directly, or frameworks like LangGraph, antigravity-sdk-python's distinguishing focus is: google's Python SDK for building AI agents on the Antigravity platform and Gemini models. Pick it when that focus matches your need; the alternative may suit you better if its broader or different scope is the priority.

How do I get started?

Les autres projets de la catégorie Agents IA avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si antigravity-sdk-python ne vous convient pas.

openclaw★ 391,6 k
A personal AI that really does things — on any OS, with your data staying yours.
superpowers★ 294,9 k
An agentic skills framework & software development methodology that works.
ECC★ 275,2 k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
hermes-agent★ 252,0 k
The agent that grows with you — a Python framework for adaptive AI agents.
deepseek-harness★ 245,5 k
DeepSeek's plugin-based agent harness where everything is a plugin.

// plus en agents

Plus en Agents IA

Projets de la catégorie Agents IA proches dans le catalogue, les plus proches en étoiles de antigravity-sdk-python — continuez à explorer de part et d'autre.

morphik-core★ 3,7 k
An open-source multimodal retrieval engine for agent pipelines.
goclaw★ 3,6 k
OpenClaw rebuilt in Go — multi-tenant AI agent teams with 5-layer security in a single binary.
AgentBench★ 3,8 k
A rigorous benchmark for LLMs acting as agents.
dbhub★ 3,6 k
A token-conscious MCP server that connects AI tools to Postgres, MySQL, SQLite and more.
vocode-core★ 3,8 k
Build voice-based LLM agents with a modular, open-source toolkit.
TradingAgents-astock★ 3,6 k
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear deb…

Obtenir antigravity-sdk-python

Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.

Voir sur GitHub ↗← Plus d'outils agents IA