AI Maestro
A multi-machine dashboard for orchestrating many AI coding agents at once, giving each one persistent memory, a code-graph view of what it owns, and a messaging protocol so agents can coordinate directly instead of through a human relay.
AI Maestro is a dashboard for running many AI coding agents across multiple computers from one place, built after its author found themselves manually relaying context between dozens of agent terminals. It works with any terminal-based agent, including Claude Code, Codex, Aider, Cursor, OpenClaw or Hermes, connecting machines in a peer mesh network with no central server required.
Each agent in the system is modeled closer to an employee than a one-off job: it has a name, a memory that survives the session, an inbox, and something it owns, such as a repository or a process, which its memory and code graph stay indexed against so it improves at that specific area over time. Its Agent Messaging Protocol lets agents coordinate directly with each other, while a person orchestrates rather than manually passing messages between them; agents that share a repository each work on their own branch and integrate through git, the same way two engineers would.
It is licensed under MIT, with no account, telemetry or per-seat pricing.