Google Antigravity SDK is a Python library for building AI agents with Antigravity and Gemini, while providing the infrastructure that runs their agent loops. It is for developers creating stateful agents and supports use with Gemini Enterprise Agent Platform.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add google-antigravity/antigravity-sdk-python --skill google-antigravity-sdkgit clone --depth 1 https://github.com/google-antigravity/antigravity-sdk-pythonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/google-antigravity/antigravity-sdk-python/google-antigravity-sdk)<a href="https://agentmods.dev/skills/google-antigravity/antigravity-sdk-python/google-antigravity-sdk"><img src="https://agentmods.dev/badge/skills/google-antigravity/antigravity-sdk-python/google-antigravity-sdk/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/google-antigravity/antigravity-sdk-python/google-antigravity-sdk"><img src="https://agentmods.dev/badge/skills/google-antigravity/antigravity-sdk-python/google-antigravity-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01864 |
| Opus 5.5 | $0.00021 | $0.00746 |
| Sonnet 5.5 | $0.00011 | $0.00373 |
| Haiku 4.5 | $0.00005 | $0.00186 |
Grade A, and why
google-antigravity-sdk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- google-antigravity-sdk — 91% identical, 100 lines differ
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Antigravity SDK
Installation & Setup
Before proceeding with any Google Antigravity tasks, ensure the environment is ready:
- Verify Applicability: If operating in an existing codebase, verify that using this Python SDK is possible and appropriate for the project.
- Check Dependencies: Check if
google-antigravityis listed in the project's dependencies (e.g.,requirements.txt,pyproject.toml). - Install Package: Ensure the
google-antigravityPython package is installed. - Authentication Setup:
- The SDK defaults to hosted Gemini models with an API key
(
LocalAgentConfig). When running on-device or without cloud connectivity is desired, local models (LiteRTAgentConfigorLocalOpenAIAgentConfig) can be used as an alternative without an API key or cloud credentials. - Hosted Models (Gemini - Default): Check for a valid
GEMINI_API_KEYenvironment variable or a.envfile (required to access Gemini models).- If credentials are missing, you MUST actively help the user get set
up with an API key by providing the following link:
- Default to Google AI Studio:
https://aistudio.google.com/app/api-keys
- Default to Google AI Studio:
- Explain that the API key can be passed explicitly in code as
shorthand (e.g.,
LocalAgentConfig(api_key="...")) or automatically read from the environment. - For Gemini Enterprise Agent Platform (formerly Vertex AI)
authentication, the SDK supports both Standard Mode and Express
Mode:
- Standard Mode (ADC): Instruct the user to run
gcloud auth application-default loginand configure the agent withvertex=Truealong withprojectandlocationinLocalAgentConfig. - Express Mode (API Key): Configure the agent with
vertex=Truealong withapi_key="your-express-api-key"inLocalAgentConfig(no ADC or regional project/location needed).
- Standard Mode (ADC): Instruct the user to run
- If credentials are missing, you MUST actively help the user get set
up with an API key by providing the following link:
- Local Models (Alternative): For local models (
LiteRTAgentConfigorLocalOpenAIAgentConfig), no API key or cloud credentials are needed. LiteRT is the supported on-device runtime for local models (such as Gemma 4 26B). Seereferences/local_models.mdandexamples/getting_started/local_models.mdfor setup details.
- The SDK defaults to hosted Gemini models with an API key
(
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/getting_started/agent_skills.md 1.6 KB
- examples/getting_started/app_data_dir_override.md 1.0 KB
- examples/getting_started/budget_limits.md 3.3 KB
- examples/getting_started/cancellation.md 1.8 KB
- examples/getting_started/compaction.md 1.4 KB
- examples/getting_started/custom_tool.md 3.7 KB
- examples/getting_started/customizing_retries.md 2.6 KB
- examples/getting_started/hello_world.md 2.6 KB
- examples/getting_started/hooks.md 4.2 KB
- examples/getting_started/local_models.md 6.1 KB
- examples/getting_started/mcp_tools.md 4.1 KB
- examples/getting_started/multimodal.md 1.8 KB
- examples/getting_started/periodic_trigger.md 2.7 KB
- examples/getting_started/persistence.md 1.4 KB
- examples/getting_started/persona_config.md 2.2 KB
- examples/getting_started/structured_output.md 1.3 KB
- examples/getting_started/subagents.md 3.3 KB
- examples/getting_started/web_tools.md 2.2 KB
- examples/getting_started/workflows.md 4.8 KB
- references/agent_configuration.md 12 KB
- references/architecture.md 3.3 KB
- references/built_in_tools.md 3.6 KB
- references/error_handling.md 3.3 KB
- references/local_models.md 7.6 KB
- references/mcp_integration.md 5.8 KB
- references/observability.md 2.9 KB
- references/safety_policies.md 7.5 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed · +4 lines 30d9586004e9
- 23d ago Changed · +11 lines 6bdbe182a6eb
- 29d ago Changed 1cc559fab1ca
- 1mo ago Changed · +4 lines 40b883270767
- 1mo ago First seen · 129 lines · 53 tokens per session scan A dd5d6b325329
google-antigravity-sdk is a skill published in the GitHub repository google-antigravity/antigravity-sdk-python (3,750 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,864 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
conductor-setup
Scaffolds the project and sets up the Conductor environment. Use this whenever a project needs to be initialized or if the Conductor configuration is missing.
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.
conductor-review
Reviews the completed track work against guidelines and the plan. Acts as a Principal Software Engineer to ensure quality and compliance.
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.
conductor-revert
Reverts previous work (tracks, phases, or tasks) by identifying associated commits and performing Git reverts.
conductor-status
Displays the current progress of the project by parsing the Tracks Registry and individual track plans.