# google-antigravity/antigravity-sdk-python

A Python library for building AI agents that leverage the full power of Google Antigravity.

Repository: https://github.com/google-antigravity/antigravity-sdk-python
Canonical: https://ross.abutalabs.com/products/antigravity-sdk-python
Homepage: https://antigravity.google/product/antigravity-sdk
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai-agents, antigravity, gemini, gemini-api, google, llm-agents, mcp, python-sdk, skills
Last push: 2026-08-26T19:04:13+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 9
- inputs: {"age_days": 126, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3185, forks 1273 (observed 2026-08-28T04:07:47.760922+00:00)

## What it is
A Python SDK for building AI agents powered by Google Antigravity and Gemini, abstracting the agentic loop behind a stateful, secure infrastructure layer. It ships as platform-specific wheels with a compiled runtime binary and supports both Gemini API keys and Vertex AI (Gemini Enterprise Agent Platform) authentication.

## Use cases
- build ai agents in python with gemini
- create a chatbot backed by google gemini
- run agents on vertex ai with gcp credentials
- stream llm agent responses in real time
- wire mcp tools into a gemini agent
- prototype an agent with system instructions

## When to choose
- you want a managed agentic loop instead of hand-rolling tool wiring and lifecycle
- you are on Google's stack (Gemini API or Vertex AI) and prefer a first-party SDK
- you need streaming agent output for console or UI apps

## When to avoid
- you need a fully open, inspectable runtime - the core is a compiled binary in the wheel
- you want provider-agnostic agents across non-Google models
- you need to run from source without installing from PyPI

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, llm-inference, mcp, sdk
- domain: large-language-models, developer-tools
- platform: python, cross-platform
- tags: gemini, google, vertex-ai, agentic-loop, python-sdk, ai-agents

## Member repositories
- google-antigravity/antigravity-sdk-python (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.760922+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:25:00.353678+00:00, confidence not recorded.
  - readme: https://github.com/google-antigravity/antigravity-sdk-python (fetched 2026-08-28T04:07:47.760922+00:00, sha 32720bee8e66)
  - homepage: https://antigravity.google/product/antigravity-sdk (fetched 2026-08-29T09:38:55.811902+00:00, sha dae0da1dc7ff)
- Data as of 2026-08-30T08:39:29.467469+00:00.