Maestro is a cross-platform desktop application designed to manage and orchestrate fleets of AI agents for software development. It targets power users and developers who juggle multiple projects, offering a keyboard-first interface to enhance focus and productivity. Maestro enables parallel AI agent execution, automated workflows, and collaborative AI discussions, streamlining complex development tasks and improving developer velocity.

How It Works

Maestro employs a novel approach centered around Git Worktrees, allowing multiple AI agents to operate in parallel on isolated branches of a project without conflicts. Its "Auto Run" feature processes markdown checklists as playbooks, executing tasks sequentially in fresh AI sessions for clean context. A "Group Chat" function coordinates multiple agents, with a moderator AI synthesizing responses for complex queries. The application prioritizes a keyboard-first, highly responsive interface for efficient workflow management.

Quick Start & Requirements

Installation involves downloading the latest release from the Releases page or building from source via git clone https://github.com/pedramamini/Maestro.git, followed by npm install and npm run dev. Prerequisites include at least one authenticated AI coding agent (Claude Code, OpenAI Codex, or OpenCode) and optionally Git. Full documentation is available at docs.runmaestro.ai.

Highlighted Details

• Parallel Development: Utilizes Git Worktrees for true parallel agent execution on isolated branches, simplifying PR creation.
• Automated Workflows: "Auto Run & Playbooks" enable batch processing of tasks and repeatable workflows with full history tracking.
• Multi-Agent Coordination: "Group Chat" allows multiple AI agents to collaborate under a moderator AI.
• Remote Access & CLI: Features built-in mobile remote control via a web server and a full CLI (maestro-cli) for headless operation.
• Developer Experience: Offers dual-mode sessions (AI/Command Terminal), extensive keyboard shortcuts, session discovery, and integrated Git/file explorers.
• Analytics: Includes a "Usage Dashboard" for tracking AI patterns and a "Document Graph" for visualizing markdown documentation relationships.
• Cost Management: Real-time token usage and cost tracking per session and globally.

Maintenance & Community

Community support is available via a Discord server. Bug reporting and feature requests can be submitted through GitHub Issues. Contribution guidelines are detailed in CONTRIBUTING.md.

Licensing & Compatibility

Maestro is licensed under the AGPL-3.0 License. This strong copyleft license requires derivative works to be shared under the same license, which may impose restrictions on integration with proprietary software.

Limitations & Caveats

Current agent support is limited to Claude Code, OpenAI Codex, and OpenCode, with plans to add more based on user demand. The README does not explicitly state an alpha or beta status, but the extensive feature set suggests a mature project.