Maestro: a cross-platform orchestrator for managing a fleet of AI coding agents and parallel projects
Maestro: a cross-platform orchestrator for managing a fleet of AI coding agents and parallel projects
What it solves
Maestro is a cross-platform desktop application designed for power users and developers who manage multiple AI coding agents and projects simultaneously. It eliminates the fractured attention caused by juggling various AI tools, providing a unified interface to orchestrate a fleet of agents across different providers.
How it works
Maestro acts as a pass-through to existing AI providers (such as Claude Code, OpenAI Codex, and OpenCode). It leverages the tools, permissions, and authentication already configured in those providers. Instead of interactive sessions, it manages tasks as prompt-response pairs, allowing for non-interactive execution of tasks in fresh sessions with clean context.
Who it’s for
It is built for "hackers" and power users who prefer keyboard-first workflows, high-velocity development, and the ability to run multiple AI agents in parallel across isolated git branches.
Highlights
- Git Worktrees: Run AI agents on isolated branches in separate directories to enable parallel development without merge conflicts.
- Auto Run & Playbooks: Batch-process markdown checklists as repeatable workflows, where each task is executed in a fresh AI session.
- Group Chat: Use a moderator AI to coordinate and route questions across multiple agents for architecture discussions.
- Keyboard-First Design: Extensive customizable shortcuts and a
Cmd+Kquick actions palette for maximum flow state. - Mobile Remote Control: Monitor and control agents via a built-in web server accessible via QR code.
- Integrated Tooling: Includes a dual-mode AI/Command terminal, file explorer with
@mentions, and a visual document graph for markdown documentation.
Sources
- undefinedRunMaestro/Maestro