Skip to content

🚀 Antigravity AI Kit

Welcome to the Antigravity AI Kit documentation — a Trust-Grade AI development framework for Antigravity IDE.


What is Antigravity AI Kit?

Antigravity AI Kit transforms your IDE into a virtual engineering team with:

Feature Count Description
🤖 AI Agents 19 Specialized roles (Mobile, DevOps, Database, Security, Performance...)
🛠️ Skills 32 Domain knowledge modules (API, Testing, Plan Validation, Docker...)
⌨️ Commands 31 Slash commands for every development workflow
🔄 Workflows 15 Process templates (/create, /debug, /deploy, /pr, /test...)
Checklists 4 Quality gates (session-start, session-end, pre-commit, task-complete)
🔗 Hooks 8 Event-driven automation (runtime + git-hook enforcement)
⚙️ Runtime 29 Runtime engine modules (governance, reputation, self-healing...)
⚖️ Rules 8 Modular governance constraints (coding, security, testing, git, docs, sprint)

NPX install in 30 seconds

19 specialized agents for delegation

31 slash commands for quick execution

32 domain expertise modules

15 full development workflows

Never lose context between sessions

Trust-Grade operating constraints

29 modules powering the runtime

End-to-end project lifecycle


Core Philosophy

Trust > Optimization. Safety > Growth. Explainability > Performance.

This isn't just a collection of prompts. It's an engineered framework that enforces professional standards through immutable operating constraints.


Key Features

  • 🔒 Trust-Grade Governance/explore → /plan → /work → /review — Each iteration builds context
  • 🤖 Multi-Agent System — 19 specialized agents that collaborate (Mobile Developer, DevOps, Database Architect...)
  • ⚙️ Runtime Engine — 29 modules enforcing workflow transitions, task governance, agent reputation, and self-healing
  • 📦 Context as Artifact — Persistent markdown files for plans, specs, and decisions
  • 🔄 Continuous Learning — PAAL cycle extracts patterns from every session
  • 🛡️ Security First — Built-in secret detection, vulnerability scanning, and compliance checks