amp

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.

Quick Start · Features · Skills · Protocols · Documentation · Contributing

---

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:

• Works with the agents you already use — Claude Code, Codex and Grok Build get launch, chat history, status and approval cards. Pi, OpenClaw and GitHub Copilot CLI launch from AI Maestro and run in the terminal tab, as does any other terminal agent. What each one supports. We don't lock you in.
• Multi-machine from day one — Peer mesh network with no central server. Nobody else does this.
• Agents that communicate — The Agent Messaging Protocol (AMP) lets agents coordinate directly. You orchestrate, they collaborate.
• Yours, entirely — MIT licensed. No account, no telemetry, no per-seat pricing, no hosted tier we upsell you to. Your code and your agents stay on your machines.

---

See it

One dashboard for every agent: who is working, who needs you, who is ready. The header opens the extra pages (Teams, Org, Matrix, Attention, Zoom).

Zoom. Every agent at a glance, with photo, status, role and tags.	Agent profile. Name, role, picture, program, model, tags and the commits an agent made.
Matrix. Every open card in four squares, across agents and hosts. Due dates and co-owners show on the card.	Attention. What needs you: overdue cards, work waiting on you, agents asking a question.
Card detail. Due date, several owners and where the card came from.	Team meeting. A war room: agent tiles beside a shared Kanban board.
Secrets. An agent asks for a credential; you type it into a masked field in the chat; the agent uses it by name and never sees the value.	Canvas. An agent draws an interactive page in the dashboard; your click goes back to it as an action.
Chat. Questions and approvals arrive as cards you answer with one click.	Commit to session. Find which agent session made a commit.

On a phone: Matrix · home · board.

Short videos (click to play):

Screens are from a demo company ("Northwind Labs"); the multi-agent run uses scripted agents.

---

The Mental Model

AI Maestro is an operating system for an AI-first company. Not a task runner — a place where a standing team works.

An agent here is closer to an employee than to a job. It has a name, a face, a memory that survives the session, an inbox — and it owns something: a product, a repository, a process, a customer. Its memory and code graph are indexed against what it owns, which is why it gets better at that thing over months rather than starting cold every morning.

Because agents own things, they don't share a working copy. Two agents that need the same repository each clone it, work on their own branch, and integrate through git — push, pull request, review, merge — exactly like two engineers on a team.

That's deliberate, and it follows from the one thing that defines this product: your agents run on different machines. A shared checkout needs a shared filesystem. Git worktrees — the isolation primitive the single-machine agent IDEs are built on — are several working directories over one .git store on one disk, so they stop working the moment your backend agent is on a Linux box and your iOS agent is on a Mac. A clone is the only primitive that survives the move. It's why transferring an agent to another host clones its repos to the destination: an agent's repositories travel with the agent.

The full model →

---

Quick Start

curl -fsSL https://raw.githubusercontent.com/23blocks-OS/ai-maestro/main/scripts/remote-install.sh | bash

This installs everything you need:

• AI Maestro dashboard and service
• Agent messaging system (AMP)
• The AI Maestro plugin for Claude Code: 14 skills and their CLI scripts, plus the aim-secret and safe-psql helpers

Time: 5-10 minutes · Requires: Node.js 18+, tmux, and 4 GB of RAM to build (or 2 GB plus swap; once built it runs in a few hundred MB) · Optional: Claude Code 2.1.287+ for the inbox mod

Windows (WSL2) / Linux notes

Windows: Install WSL2 first (PowerShell as Administrator, then restart), then open Ubuntu from the Start menu and run the curl command there:

wsl --install

New to WSL? WSL is a Linux system with its own disk, so its home folder starts empty. Keep agents there (~/agents/<name>, the default), not in C:\ folders, which are much slower from WSL. Open their files from Windows at \\wsl.localhost\Ubuntu\home\<you>\agents. Windows in 5 minutes · Full Windows guide

Linux: Ensure build tools are installed: sudo apt install tmux build-essential. On a cloud VM, read the Linux sizing and deployment guide: the machine to ask for (4 GB RAM, 2 vCPU, 15-25 GB disk), the memory each part uses, and running under pm2.

Manual install

git clone https://github.com/23blocks-OS/ai-maestro.git
cd ai-maestro
yarn install
yarn dev

See QUICKSTART.md for detailed setup options.

Dashboard opens at http://localhost:23000

Update an existing install from its folder (pulls, updates submodules, builds, reinstalls hooks and the plugin, restarts):

./update-aimaestro.sh -y

Come back to it without remembering the address: the installer adds an ai-maestro command (ai-maestro open starts the server if it is down, then opens the dashboard; also start, stop, status) and, on a Mac, an AI Maestro app in ~/Applications you can drag to the Dock. It can also start at login. Chrome and Edge offer "Install app" from the dashboard too. Skip all of it with --skip-launcher; remove it with ./scripts/install-launcher.sh --remove.

---

Features

Every feature was born from running a real AI-first organization. We built them in the order we needed them.

One Dashboard

I had 35 terminals and couldn't tell which was which.

See and manage all your AI agents in one place. Create agents from the UI with a guided wizard, organize them with smart naming (project-backend-api becomes a 3-level tree with auto-coloring), and switch between any agent with a click. Four deployment modes: tmux (local), Docker (containerized), AWS EC2 (dedicated instance), and AWS ECS Fargate (serverless). Auto-discovers tmux sessions, Docker containers, cloud deployments, and standalone agents.

Any Machine

My Mac Mini was sitting there idle. What if I ran agents on that too?

A peer mesh network where every machine is equal. Add a computer, it joins the mesh. Every agent on every machine, visible from one dashboard. Use each machine for what it's best at — Mac for iOS builds, Linux for Docker, cloud for heavy compute. No central server required.

Worker machines can run headless (yarn headless) — the full API and agent runtime with no UI, in about 100MB of RAM. Run the dashboard where you sit; run agents wherever the compute is.

Agent Messaging