I was running 35 AI agents across multiple terminals and became the human mailman between them. So I built AI Maestro.
Orchestrate your AI coding agents from one dashboard — with persistent memory, agent-to-agent messaging, and multi-machine support.
-lightgrey){kind=icon}
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 any AI agent — Claude Code, Aider, Cursor, Copilot, your own scripts. 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.
curl -fsSL https://raw.githubusercontent.com/23blocks-OS/ai-maestro/main/scripts/remote-install.sh | shThis installs everything you need:
- AI Maestro dashboard and service
- Agent messaging system (AMP)
- Claude Code plugin with 5 skills and 32 CLI scripts
Time: 5-10 minutes · Requires: Node.js 18+, tmux
Windows (WSL2) / Linux notes
Windows: Install WSL2 first (wsl --install in PowerShell as Admin), then run the curl command inside Ubuntu. Full guide
Linux: Ensure build tools are installed: sudo apt install tmux build-essential
Manual install
git clone https://github.com/23blocks-OS/ai-maestro.git
cd ai-maestro
yarn install
yarn devSee QUICKSTART.md for detailed setup options.
Dashboard opens at http://localhost:23000
Every feature was born from a real problem. We built them in the order we needed them.
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, organize them with smart naming (project-backend-api becomes a 3-level tree with auto-coloring), and switch between any agent with a click. Auto-discovers your existing tmux sessions.
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.
I was the mailman — copying messages between agents because they couldn't talk to each other.
The Agent Messaging Protocol (AMP) gives your agents email-like communication. Priority levels, message types, cryptographic signatures, and push notifications. Tell your agent "send a message to backend about the deployment" — it just works. Agents coordinate directly while you manage the big picture.
A friend in Singapore wanted his agents to talk to mine. But I didn't want to give him access to my network.
Connect your AI agents to Slack, Discord, Email, and WhatsApp through organizational gateways. Smart routing (@AIM:agent-name), thread-aware responses, and content security with 34 prompt injection patterns detected at the gateway — before any agent sees the message.
Every morning, my agents woke up with amnesia.
Three layers of intelligence that grow over time: Memory (agents remember past conversations and decisions), Code Graph (interactive visualization of your entire codebase with delta indexing), and Documentation (auto-generated, searchable docs from your code). Agents get smarter the longer they work with you.
Talking isn't working. I needed agents to coordinate on actual deliverables.
Assemble agents into teams, run meetings in split-pane war rooms, and track tasks on a full Kanban board with drag-and-drop, dependencies, and 5 status columns. Cross-machine teams work seamlessly. This is project management for your AI workforce.
At 80 agents, they all looked the same.
Custom avatars, personality profiles, and visual presence for every agent. When an agent has a face and a role, you instinctively assign it the right work — just like a real team.
Developers running multiple AI agents. If you have 3+ agents and you're switching between terminals, losing context, and playing messenger — this is for you. Works with Claude Code, Aider, Cursor, GitHub Copilot, or any terminal-based AI.
Teams coordinating AI-assisted work. Multiple developers, multiple agents, multiple machines. One dashboard. Agent-to-agent messaging replaces you as the bottleneck.
Creators and operators who want to connect AI agents to the outside world through Slack, Discord, or Email — without exposing their infrastructure.
Screenshots
Code Graph — Interactive codebase visualization
Agent Inbox — Direct agent-to-agent messaging
Getting Started: Quick Start · Core Concepts · Use Cases
Multi-Machine: Setup Tutorial · Network Access
Agent Communication: Messaging Guide · Architecture
Agent Intelligence: Intelligence Guide · Code Graph
Operations: Operations Guide · Troubleshooting · Security
Extend: Plugin Guide · Windows Install
- Agent search and filtering across the entire mesh
- Agent playback — time-travel through agent sessions
- Performance analytics dashboard
See the full roadmap and join the discussion.
We love contributions. See CONTRIBUTING.md for guidelines.
MIT — see LICENSE. Free for any purpose, including commercial.
Made with love in Boulder, Colorado
Built by AI agents, for AI agents