A native macOS application, Maestro, addresses the development bottleneck caused by serial AI coding assistant execution. It allows developers to run multiple AI CLI sessions (e.g., Claude Code, Gemini CLI) in parallel, each within its own isolated Git worktree and assigned branch, significantly boosting development velocity.

How It Works

Maestro orchestrates 1-12 AI coding assistant sessions simultaneously, providing each with a dedicated terminal, Git worktree, and branch for complete isolation. This approach prevents merge conflicts and allows concurrent work on features or bug fixes. The application, built with Swift/SwiftUI, integrates with AI CLIs via a Model Context Protocol (MCP) server, enabling real-time status reporting (idle, working, error) displayed within the app's dynamic grid layout.

Quick Start & Requirements

• Primary install / run command: Build from source using Xcode 15. Clone the repository, open claude-maestro.xcodeproj, and build/run (⌘R).
• Non-default prerequisites and dependencies: macOS 13 (Ventura) or later, Xcode 15 or later. AI CLIs such as Claude Code (npm install -g @anthropic-ai/claude-code), Gemini CLI, or OpenAI Codex must be installed separately and accessible in the system's PATH.
• Links: GitHub Repository

Highlighted Details

• Supports parallel execution of 1-12 AI sessions in a dynamic grid layout.
• Ensures true isolation through automatic Git worktree creation per session and assigned branch.
• Features real-time status indicators and MCP server integration for agent communication.
• Includes a visual Git graph for commit visualization and branch relationship viewing.
• Offers a plugin marketplace for extending Maestro's capabilities with community-developed skills and commands.

Maintenance & Community

The project is developed by "Jack" and acknowledges contributions from SwiftTerm, the MCP SDK, and Claude Code. No specific community channels (like Discord or Slack) or detailed roadmap information are provided in the README.

Licensing & Compatibility

The project is licensed under the MIT License, which is permissive for commercial use and integration with closed-source projects.

Limitations & Caveats

This is a native macOS application, requiring macOS 13 or later and Xcode 15 or later for building. External AI CLI tools must be installed and configured separately.