#6161st of 87 in Coding agents and assistants
maestro
Desktop app for running many coding agents in parallel with unattended playbooks
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.5k
- License
- AGPL-3.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
Overview
Maestro is a cross-platform desktop app that wraps CLI coding agents (Claude Code, Codex, OpenCode, Factory Droid, plus beta Copilot-CLI, Qwen3 Coder and Oh My Pi) and runs them side by side, each with its own workspace and history. Auto Run executes markdown checklists or free-text goals as playbooks, one fresh session per task, and git worktrees isolate parallel agents. A built-in web server gives phone access, and a maestro-cli runs playbooks headless.
Who it is for: Developers running several CLI coding agents across projects, keyboard-first
Strengths
- Passes through existing Claude Code, Codex or OpenCode config, MCP tools, skills and auth unchanged
- Auto Run playbooks start a fresh session per task, suited to long unattended runs
- Git worktree sub-agents run in parallel on isolated branches, with PR creation from the app
- maestro-cli runs playbooks from cron or CI with JSONL output
Weaknesses
- Needs at least one supported agent CLI installed and authenticated separately
- AGPL-3.0 license may restrict use in proprietary products
- Copilot-CLI, Qwen3 Coder and Oh My Pi support is beta; Gemini CLI not supported
- Tasks are prompt and response, not interactive agent sessions
What it needs
- no GPU
- Needs Claude Code, Codex, OpenCode or another supported agent CLI, Git (optional), Cloudflare tunnel (optional, remote access)
- Models: Claude Code, OpenAI Codex, OpenCode, Factory Droid, Copilot-CLI (beta)
Also in Coding agents and assistants
See all 87| Rank | Project | Score |
|---|---|---|
| 1 | claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs | 83 out of 100 |
| 2 | ArchonYAML workflow engine that runs AI coding agents through fixed dev steps | 82 out of 100 |
| 3 | oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory | 80 out of 100 |
| #4 | Open SWELangChain coding agent that plans, implements and reviews pull requests | 80 out of 100 |
| #5 | opencodeTerminal coding agent with build and plan modes, plus a desktop app | 79 out of 100 |