Antigravity Manager logo

Antigravity Manager

CommunityPopular
Draculabo
antigravity-manager

Comprehensive guide to Antigravity Manager architecture, workflows, and development. Use this to understand how to work on the project.

Overview

PublisherDraculabo
RepositoryAntigravityManager
Skill nameantigravity-manager
Stars
2.4K
Forks
285
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Draculabo on GitHub. Read the source before you install it.

Installation

Install the Antigravity Manager AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Draculabo/AntigravityManager/tree/main/.agent/skills/project_overview
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Draculabo/AntigravityManager.git /tmp/AntigravityManager
mkdir -p .claude/skills
cp -r /tmp/AntigravityManager/.agent/skills/project_overview .claude/skills/antigravity-manager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Antigravity Manager in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Antigravity Manager on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Antigravity Manager is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Antigravity Manager Developer Guide

🏗️ Architecture Overview

Antigravity Manager is a hybrid Desktop Application built with Electron, React, and NestJS. It follows a modular architecture where the frontend (Renderer) communicates with the backend (Main) via type-safe IPC (ORPC).

Key Technologies

  • Frontend: React 19, TailwindCSS v4, TanStack Router, TanStack Query.
  • Backend: Electron (Main), NestJS (Core Logic), Better-SQLite3 (Data).
  • Communication: ORPC (Type-safe IPC wrapper around Electron IPC).
  • Build: Electron Forge + Vite.

📂 Directory Structure

  • src/main.ts: Electron Main Process entry point.
  • src/preload.ts: Bridge between Main and Renderer.
  • src/renderer.tsx: React App entry point.
  • src/components/: Reusable React UI components (Radix UI based).
  • src/ipc/: IPC Routers and Handlers (Domain logic).
    • router.ts: Main ORPC router definition.
    • account/, cloud/, database/: Domain-specific handlers.
  • src/server/: NestJS application modules (proxies/gateways).
  • src/services/: Core business logic (framework agnostic).
    • GoogleAPIService.ts: Gemini/Cloud interactions.
    • AutoSwitchService.ts: Account rotation logic.
  • src/routes/: Frontend routing definitions (File-based).

🚀 Development Workflow

Prerequisites

  • Node.js 18+
  • npm (Project uses package-lock.json)

Common Commands

  • Start Dev Server: npm start
  • Lint Code: npm run lint
  • Unit Test: npm run test:unit
  • E2E Test: npm run test:e2e
  • Build Production: npm run make

🧠 Core Concepts

IPC Communication (ORPC)

The project uses orpc for type-safe communication.

  • Define: Create a router in src/ipc/router.ts with Zod schemas.
  • Implement: Add logic in handlers (e.g., src/ipc/account/handler.ts).
  • Call: Use the generated client in React components.

Database Access

Data is stored in a local SQLite file.

  • Use Better-SQLite3 for direct access.
  • Logic should be encapsulated in src/services or src/ipc.

Account Management

  • Accounts are added via OAuth (Google/Claude).
  • GoogleAPIService handles token exchange and refreshing.
  • AutoSwitchService monitors usage and switches active accounts automatically.

⚠️ Critical Rules

  1. Type Safety: strict TypeScript usage; Zod for runtime validation.
  2. Components: Use src/components/ui (Radix primitives) for consistency.
  3. Async: Handle all IPC/DB calls asynchronously with try/catch.
  4. Security: Never commit secrets. API keys are user-provided or encrypted locally.

Frequently asked questions

What does the Antigravity Manager AI skill do?

Comprehensive guide to Antigravity Manager architecture, workflows, and development. Use this to understand how to work on the project.

Why use Antigravity Manager on TypingMind?

Because you install it once and use it with any model. Antigravity Manager is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Antigravity Manager in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Draculabo/AntigravityManager/tree/main/.agent/skills/project_overview. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Antigravity Manager?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Antigravity Manager?

As many as you like. As long as a model supports skills, you can use Antigravity Manager with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Antigravity Manager AI skill free?

It is published on GitHub by Draculabo. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇