Download
Download the latest release for your platform from the Releases page:- macOS:
.dmgor.zip(available for both Intel and Apple Silicon) - Windows:
.exeinstaller or portable.exe(no installation required) - Linux:
.AppImage,.deb, or.rpm(available for both x86_64 and arm64) - Upgrading: Simply replace the old binary with the new one. All your data (sessions, settings, playbooks, history) persists in your config directory.
Requirements
- At least one supported AI coding agent installed and authenticated:
- Claude Code - Anthropic’s AI coding assistant (fully integrated)
- Codex - OpenAI’s coding agent (fully integrated)
- OpenCode - Open-source AI coding assistant (fully integrated)
- Factory Droid - Factory’s AI coding assistant (fully integrated)
- Copilot-CLI - GitHub’s terminal coding agent (beta integration, multi-model via models.dev)
- Hermes - Nous Research’s AI coding agent (beta integration)
- Pi - A customizable AI agent harness (beta integration)
- Qwen3 Coder - Alibaba’s Qwen Code agent, a Gemini CLI fork (beta integration)
- Oh My Pi - Multi-model coding agent (beta integration,
ompCLI) - Gemini CLI - Planned support
- Git (optional, for git-aware features)
Maestro is a pass-through to your provider. Your MCP tools, custom skills, permissions, and authentication all work in Maestro exactly as they do when running the provider directly - Maestro just orchestrates the conversation flow in batch mode.
WSL2 Users (Windows Subsystem for Linux)
Using Windows mounts causes several critical issues:Recommended WSL2 Setup
Accessing Files from Windows
You can browse your WSL2 files from Windows Explorer using:Troubleshooting WSL2
If you encounterelectron-rebuild failures, try setting the temp directory:
Building from Source
If you prefer to build Maestro from source:Building from source requires native module compilation (node-pty, better-sqlite3). On Windows, you’ll need the Visual Studio Build Tools. On macOS, you’ll need Xcode Command Line Tools (
xcode-select --install).