Claude Skill
23blocks-OS/ai-maestro
AI Maestro enhances Claude Code agents with memory search, code graph queries & agent messaging. Manage Claude, Aider, Cursor from one dashboard with multi-machine support.
Overview
Repository
Install this Skill
git clone https://github.com/23blocks-OS/ai-maestro.gitRegistry
git clone https://github.com/23blocks-OS/ai-maestro.gitgit clone https://github.com/23blocks-OS/lolabot.git
Summary
AI Maestro is an AI agent orchestrator with a skills system designed to enhance Claude Code agents. It provides capabilities like memory search, code graph queries, and agent-to-agent messaging, while offering a unified dashboard to manage Claude, Aider, and Cursor with multi-machine support.
AI Agent 编排器与技能系统 - 赋予Claude代码代理超能力：记忆检索、代码图谱查询、代理间消息传递。通过单一仪表盘管理Claude、Aider、Cursor。支持多机协作。
Key features
- AI agent orchestrator with a skills system
- Enhances Claude Code agents with memory search and code graph queries
- Enables agent-to-agent messaging
- Unified dashboard for managing Claude, Aider, and Cursor
- Multi-machine support for distributed workflows
Use cases
- Orchestrating multiple AI coding assistants in a unified workflow
- Enhancing Claude Code agents with persistent memory and code context
- Facilitating communication between different AI agents
- Managing development tools like Aider and Cursor from a central interface
- Scaling AI-assisted coding across multiple machines
README excerpt
<div align="center"> <img src="./docs/logo-constellation.svg" alt="AI Maestro Logo" width="120"/> # AI Maestro *I was running 35 AI agents across multiple terminals and became the human mailman between them. So I built AI Maestro.* **The OS for AI-first organizations — orchestrate any AI agent with persistent memory, agent-to-agent messaging, and multi-machine support.** [](https://github.com/23blocks-OS/ai-maestro/releases) [-lightgrey)](https://github.com/23blocks-OS/ai-maestro) [](./LICENSE) [](https://github.com/23blocks-OS/ai-maestro)  [Quick Start](#-quick-start) · [Features](#-features) · [Documentation](#-documentation) · [Contributing](./CONTRIBUTING.md) </div> --- ## The Story I gave an AI agent a real task — not autocomplete, a real engineering problem. It checked the code, read the logs, queried the database, and came back with the answer. That was the moment. *This thing can actually work.* Within a week I was running 35 agents across terminals. They were productive, but they couldn't talk to each other. I became the human message bus — copying context from one terminal, pasting into another. I was the bottleneck in my own AI team. **So I built AI Maestro** — one dashboard to see every agent, on every machine, with persistent memory and direct agent-to-agent communication. Today I run 80+ agents across multiple computers, building real companies with them every day. **What makes this different:**