{"id":"47dd1575-22c3-4159-a85a-0f6266e4fb0e","slug":"ratulbd-antigravity-os","kind":"mcp","name":"antigravity-os","summary":"Universal multi-agent operating system for Google Antigravity, Gemini CLI, and Claude Code with 193 pre-staged skills across 22 curated repositories.","owner":"ratulbd","repoUrl":"https://github.com/ratulbd/antigravity-os","license":"MIT","licenseTier":"permissive","trust":"community","stars":1,"match":null,"fewStars":true,"format":"mcp","createdAt":"2026-10-29T03:58:51.000Z","addedAt":"2026-10-29T09:15:52.646Z","logoUrl":"https://avatars.githubusercontent.com/u/22340544?v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools","cloud-infra","memory-knowledge"],"tags":["agentic-ai","gemini-cli","antigravity","claude-code","codebase-memory","developer-tools","google-antigravity","superpowers"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-29T09:55:05.677Z","sample":false,"url":"https://conduits.dev/tools/ratulbd-antigravity-os","language":"PowerShell","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Antigravity-OS 🚀\n\n> **The Production Runtime, Dual-Memory Architecture & 503-Skill Playbook for Google Antigravity & Universal AI Coding Agents.** \n> *Turn your AI coding assistant into a disciplined, autonomous software engineering team in under 2 minutes.*\n\n---\n\n
\n \n \n \n \n \n
\n\n---\n\n## ⚡ The 2-Minute Quickstart\n\nInstall the complete runtime, all **503+ skills and 71 specialist agents**, global MCP servers, and the 4-Pillar Synergy rules with a single command:\n\n### 🪟 Windows (PowerShell)\n```powershell\nirm https://raw.githubusercontent.com/ratulbd/antigravity-os/main/scripts/install.ps1 | iex\n```\n*(Or clone this repo and run `./scripts/install.ps1` in PowerShell as Administrator or regular user)*\n\n### 🍎 macOS (Terminal)\n```bash\ncurl -fsSL https://raw.githubusercontent.com/ratulbd/antigravity-os/main/scripts/install.sh | bash\n```\n\n### 🐧 Linux (Bash)\n```bash\ncurl -fsSL https://raw.githubusercontent.com/ratulbd/antigravity-os/main/scripts/install.sh | bash\n```\n\n---\n\n## 📊 Graphical Architecture\n\n
\n \n
\n\n```mermaid\nflowchart TD\n subgraph P1[\"Pillar 1: Prescriptive Specs\"]\n Specs[\"/docs/01_PRD.md → 06_Plan.md WHAT & WHY: Design tokens, CSS contracts, API schemas\"]\n end\n\n subgraph P2[\"Pillar 2: Structural AST Graph\"]\n AST[\"codebase-memory-mcp HOW code is wired: 158-Language Tree-sitter + SQLite AST\"]\n end\n\n subgraph P3[\"Pillar 3: Episodic Session Memory\"]\n Memory[\".trail/learnings/ + ai-memory WHAT was tried & ruled out: Prevents repeating failed bugs\"]\n end\n\n subgraph P4[\"Pillar 4: Specialist Execution & Runtime Gates\"]\n Runtime[\"Gravitas + Superpowers + Ponytail HOW code is mutated: Write-scope locks & fresh validator gates\"]\n end\n\n P1 --> P2\n P2 --> P3\n P3 --> P4\n```\n\n---\n\n## 💡 Why Antigravity-OS?\n\nModern AI agents (even frontier models like Gemini 3.8 and Claude 3.7) suffer from three fatal production issues:\n\n1. **Context Amnesia & Hallucination:** Agents forget past debugging dead-ends and repeatedly re-attempt failed fixes.\n2. **Unconstrained Scope Creep:** An agent instructed to tweak a button might edit 8 files, refactor configs, and bump package versions.\n3. **Premature \"Victory\" Declarations:** Saying *\"I have fixed the bug!\"* without actually executing a fresh test runner *after* the latest file mutation.\n\n**Antigravity-OS fixes this mechanically** by pairing:\n* **The 4-Pillar Synergy Protocol:** Strict non-overlapping layers for specs, AST graphs, episodic memory, and execution.\n* **The Gravitas Runtime (6 Invariants):** Hard write-scope locks (`allowed_write_scope`) and physical test-evidence gates.\n* **182 Battle-Tested Skills:** Production-grade capabilities from Anthropic, Supabase, Vercel, Expo, Superpowers, and more.\n\n---\n\n## 📈 Empirical Proofs: Measured Token Savings\n\n
\n \n
\n\n| Workflow Scenario | Raw LLM Baseline | Antigravity-OS Runtime | Verified Reduction |\n| :--- | :--- | :--- | :--- |\n| **Symbol Call-Chain Discovery** | **~32,000 tokens** *(Reading 5 full files)* | **~350 tokens** *(Tree-sitter AST Graph)* | **▼ 98.9%** |\n| **Investigating Known Bug** | **~28,500 tokens** *(3–4 trial-and-error loops)* | **~2,400 tokens** *(`.trail` + Gravitas gate)* | **▼ 91.5%** |\n| **New Feature Implementation** | **~24,000 tokens** *(Unconstrained scans)* | **~4,100 tokens** *(Pillar 1 `/docs` spec)* | **▼ 82.9%** |\n| **Boilerplate Minimization** | **~1,200 LOC output** *(Over-engineered)* | **~560 LOC output** *(Ponytail YAGNI filter)* | **▼ 53.3% LOC ▼ 45% Tokens** |\n\n---\n\n## 🗂️ The 23 Curated Repositories (503+ Skills & 71 Specialist Agents)\n\nAntigravity-OS automatically aggregates, normalizes, and stages skills from the most respected agent repositories:\n\n| # | Source Repository | Skills Included | Purpose & Domain |\n| :-: | :--- | :--- | :--- |\n| **1** | [`pbakaus/impeccable`](https://github.com/pbakaus/impeccable) | `impeccable` | 24 UI/UX design commands (`craft`, `audit`, `polish`, `harden`) and anti-slop rules. |\n| **2** | [`nextlevelbuilder/ui-ux-pro-max-skill`](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) | `ui-ux-pro-max`, `design-system`, `ui-styling`, `design`, `brand`, `banner-design`, `slides` | Design tokens, color palettes, typography, and HTML/Chart.js presentation slide decks. |\n| **3** | [`Nutlope/hallmark`](https://github.com/Nutlope/hallmark) | `hallmark` | Anti-template visual design, intentional layout variety, and non-generic web UI. |\n| **4** | [`dietrichgebert/ponytail`](https://github.com/dietrichgebert/ponytail) | `ponytail`, `ponytail-audit`, `ponytail-debt`, `ponytail-gain`, `ponytail-help`, `ponytail-review` | \"Lazy Senior Dev\" mode: YAGNI minimal code (▼45% output tokens, ▼53% LOC), stdlib first. |\n| **5** | [`cathrynlavery/diagram-design`](https://github.com/cathrynlavery/diagram-design) | `diagram-design` | Editorial HTML & SVG system diagrams and interactive flowcharts. |\n| **6** | [`blader/humanizer`](https://github.com/blader/humanizer) | `humanizer` | Removes AI writing tropes, filler, and inflated phrasing from UI copy and documentation. |\n| **7** | [`d4vinci/Scrapling`](https://github.com/d4vinci/Scrapling) | `scrapling` | Adaptive Python web scraping, stealth browser automation, and concurrent spiders. |\n| **8** | [`sgunin/ReverseEngineerAnything`](https://github.com/sgunin/ReverseEngineerAnything) | `reverse-engineer-anything` | Reverse-engineering binaries, protocols, JavaScript bundles, and runtime behavior. |\n| **9** | [`tonydzi/second-brain-starter-kit`](https://github.com/tonydzi/second-brain-starter-kit) | `last30days` | Nightly signal synthesis of what changed on any technical topic in the last 30 days. |\n| **10** | [`Onyx-Systems/onyx-chat-template`](https://github.com/Onyx-Systems/onyx-chat-template) | `onyx-chat-template` | Express.js + `nlp.js` + TypeORM + OpenAI hybrid conversational backend blueprint. |\n| **11** | [`obra/superpowers`](https://github.com/obra/superpowers) | `brainstorming`, `writing-plans`, `test-driven-development`, `systematic-debugging`, `verification-before-completion`, `subagent-driven-development`, etc. *(15 total)* | Strict TDD, root-cause debugging, parallel subagent dispatch, and verification workflows. |\n| **12** | [`proyecto26/system-design-skills`](https://github.com/proyecto26/system-design-skills) | `system-design`, `requirements-scoping`, `back-of-the-envelope`, `api-design`, `data-storage`, `caching`, `blob-store`, `sharded-counters`, etc. *(22 total)* | Distributed system design, QPS/storage estimation, caching, queues, and resilience. |\n| **13** | [`codewithowais/senior-backend-dev`](https://github.com/codewithowais/senior-backend-dev) | `senior-backend-dev` | Production backend engineering (Node/TS, Python, Go, Rust), Clean Architecture. |\n| **14** | [`supabase/agent-skills`](https://github.com/supabase/agent-skills) | `supabase`, `supabase-postgres-best-practices` | PostgreSQL indexing, RLS, query performance optimization, and lock-free migrations. |\n| **15** | [`vercel-labs/agent-skills`](https://github.com/vercel-labs/agent-skills) | `react-best-practices`, `composition-patterns`, `web-design-guidelines`, `writing-guidelines`, `vercel-optimize`, `deploy-to-vercel`, etc. *(9 total)* | React/Next.js waterfall elimination, bundle optimization, and React 19 patterns. |\n| **16** | [`expo/skills`](https://github.com/expo/skills) | `expo-native-ui`, `expo-router`, `expo-data-fetching`, `expo-animation`, `expo-design-system`, `eas-workflows`, `eas-update`, etc. *(23 total)* | Complete React Native and Expo engineering, routing, EAS deployments, and native UI controls. |\n| **17** | [`anthropics/skills`](https://github.com/anthropics/skills) | `frontend-design`, `mcp-builder`, `webapp-testing`, `web-artifacts-builder`, `skill-creator`, `pdf`, `docx`, `xlsx`, `pptx`, `canvas-design`, etc. *(14 total)* | Presentation decks (`pptx`), brochures/posters, Playwright testing, doc coauthoring, MCP building. |\n| **18** | [`skillcreatorai/Ai-Agent-Skills`](https://github.com/skillcreatorai/Ai-Agent-Skills) | `database-design`, `backend-development`, `llm-application-dev`, `verification-agent`, `code-documentation`, `changelog-generator`, etc. *(10 total)* | RAG patterns, LLM application architecture, changelogs, and technical documentation. |\n| **19** | [`ComposioHQ/awesome-claude-skills`](https://github.com/ComposioHQ/awesome-claude-skills) | `invoice-organizer`, `competitive-ads-extractor`, `lead-research-assistant`, `meeting-insights-analyzer`, `file-organizer`, etc. *(7 total)* | Document automation, competitor intelligence scraping, and meeting transcript analysis. |\n| **20** | [`coreyhaines31/marketingskills`](https://github.com/coreyhaines31/marketingskills) | `cro`, `sales-enablement`, `copywriting`, `copy-editing`, `product-marketing`, `lead-magnets`, `ad-creative`, `pricing`, `seo-audit`, etc. *(52 total)* | Full-funnel growth engineering, conversion rate optimization, sales decks, and SEO audits. |\n| **21** | [`udaysharmadev/Gravitas`](https://github.com/udaysharmadev/Gravitas) | `gravitas`, `gravitas-highstakes`, `gravitas-perf`, `gravitas-python`, `gravitas-security`, `gravitas-typescript` *(6 total)* | Engineering reliability runtime: 6 core invariants, `allowed_write_scope` lock, and validator gates. |\n\n---\n\n## 🛡️ The Gravitas Reliability Contract (6 Invariants)\n\nAntigravity-OS incorporates the **Gravitas Runtime Engine** to govern how code is inspected and modified:\n\n1. **Ground before mutating:** Read target files, tests, and callers before editing. Never assume file state.\n2. **Stay in declared scope:** Writes outside `allowed_write_scope` are rejected at the tool-call level.\n3. **Completion needs evidence:** A task is only complete when a validator (test/build/lint) passes *after* the latest file edit.\n4. **Never exact-retry a failure:** Byte-identical tool retries on failures are blocked, forcing a root-cause pivot.\n5. **Satisfy the contract:** Acceptance criteria in `contract.json` mechanically gate completion.\n6. **Say what you can't verify:** Downgrade confidence on unverified assumptions rather than fabricating certainty.\n\n---\n\n## 🔍 Health Check & Diagnostic Tool\n\nVerify that your system is correctly configured at any time:\n\n### On Windows (PowerShell):\n```powershell\n./scripts/verify.ps1\n```\n\n### On macOS / Linux (Bash):\n```bash\n./scripts/verify.sh\n```\n\n**Expected Diagnostic Output:**\n```text\n================================================================================\n ANTIGRAVITY-OS SYSTEM DIAGNOSTIC & VERIFICATION\n================================================================================\n1. SKILL INVENTORY AUDIT:\n [✓] Gemini Skills Path (~/.gemini/config/skills): 602 skills detected (Target: 503+)\n [✓] Universal Agent Skills Path (~/.agents/skills): 601 skills detected (Target: 503+)\n [✓] Critical Skill [gravitas]: Installed and resolvable\n [✓] Critical Skill [using-superpowers]: Installed and resolvable\n [✓] Critical Skill [ponytail]: Installed and resolvable\n [✓] Critical Skill [continuous-learning-v2]: Installed and resolvable\n [✓] Critical Skill [agent-security-hardening]: Installed and resolvable\n [✓] Critical Skill [design-system-audit]: Installed and resolvable\n\n2. SPECIALIST AGENT PERSONAS AUDIT:\n [✓] Specialist Agent Personas (~/.gemini/config/agents): 71 personas detected\n\n3. MCP SERVERS CONFIGURATION:\n [✓] Context7 MCP Server: Configured with @upstash/context7-mcp\n [✓] Playwright MCP Server: Configured with @playwright/mcp\n\n4. MANDATORY ATTRIBUTION & DUAL-MEMORY RULES:\n [✓] Rule .gemini/GEMINI.md: Enforcing 4-Pillars & Token Ledger\n [✓] Rule .gemini/AGENTS.md: Enforcing 4-Pillars & Token Ledger\n [✓] Rule .agents/AGENTS.md: Enforcing 4-Pillars & Token Ledger\n [✓] Rule .claude/CLAUDE.md: Enforcing 4-Pillars & Token Ledger\n\nDiagnostic Summary: All checks passed.\n================================================================================\n```\n\n---\n\n## 🌐 Universal IDE & Model Interoperability\n\nAntigravity-OS installs into universal skill discovery roots, making your 503+ skills, 71 specialist agents, and dual-memory rules instantly available across:\n\n| Platform / Assistant | Supported Paths | Status |\n| :--- | :--- | :-: |\n| **Google Antigravity** | `%USERPROFILE%\\.gemini\\config\\skills\\` | 🟢 Native |\n| **Gemini CLI** | `~/.gemini/config/skills/` | 🟢 Native |\n| **Claude Code** | `~/.claude/CLAUDE.md` + `~/.agents/skills/` | 🟢 Native |\n| **Cursor IDE** | `.cursorrules` + `~/.agents/skills/` | 🟢 Native |\n| **Windsurf IDE** | `.windsurfrules` + `~/.agents/skills/` | 🟢 Native |\n| **Cline / Roo Code** | `.clinerules` + `~/.agents/skills/` | 🟢 Native |\n| **OpenCode** | `~/.agents/skills/` | 🟢 Native |\n\n---\n\n## 🤝 Contributing & Skill Attribution\n\nAntigravity-OS stands on the shoulders of the open-source community. All skills maintain their upstream licenses and attributions. If you would like to contribute a new skill repository or improve runtime hooks:\n\n1. Fork the repository.\n2. Create your feature branch (`git checkout -b feature/awesome-skill`).\n3. Commit your changes and open a Pull Request.\n\n---\n\n## 📄 License\n\nDistributed under the **MIT License**. See [`LICENSE`](./LICENSE) for full details.\n"}
![\"License](\"https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge\"){kind=icon}
\n ![\"Platform](\"https://img.shields.io/badge/Platform-Windows%20%7C%20macOS%20%7C%20Linux-emerald.svg?style=for-the-badge\"){kind=icon}
\n ![\"503+](\"https://img.shields.io/badge/Curated%20Skills-503%2B%20Skills-violet.svg?style=for-the-badge\"){kind=icon}
\n ![\"23](\"https://img.shields.io/badge/Canonical%20Repos-23%20Repos-orange.svg?style=for-the-badge\"){kind=icon}
\n ![\"Token](\"https://img.shields.io/badge/Token%20Savings-Up%20to%2095%25-green.svg?style=for-the-badge\"){kind=icon}
\n![\"Antigravity-OS](\"./assets/architecture.svg\")
\n![\"Token](\"./assets/token-savings.svg\")
\n