# RunMaestro/Maestro

Agent Orchestration Command Center

Repository: https://github.com/RunMaestro/Maestro
Canonical: https://ross.abutalabs.com/products/runmaestro-maestro
Homepage: https://RunMaestro.ai
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: ai-agents, claude-code, generative-ai, codex, opencode
Last push: 2026-08-26T22:16:00+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 79, longevity 20
- inputs: {"age_days": 284, "days_push": 7, "days_rel": 60, "gap_med": 0, "n_releases_24m": 62}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3284, forks 348 (observed 2026-08-28T04:07:53.700023+00:00)

## What it is
Maestro is a cross-platform desktop application for orchestrating fleets of AI coding agents such as Claude Code, Codex, OpenCode, Factory Droid, and Copilot-CLI. It provides a keyboard-first interface for running multiple agents in parallel, with Auto Run playbooks, git worktree isolation, group chat, and event-driven automation for long unattended sessions.

## Use cases
- run multiple AI coding agents in parallel
- execute long unattended agent sessions overnight
- batch-process markdown task checklists with AI agents
- run agents on isolated git worktree branches
- orchestrate Claude Code and Codex from one desktop app
- trigger agent prompts on file changes or GitHub events
- manage a fleet of AI agents across projects

## When to choose
- you juggle multiple AI coding agents and projects in parallel
- you want keyboard-first, Linear/Superhuman-style speed managing agents
- you need unattended long-running agent execution with clean per-task context
- you want git worktree-based parallel development with one-click PRs

## When to avoid
- you only use a single agent interactively and are happy with the raw CLI
- you need a web-based or team-shared orchestration platform rather than a local desktop app
- you rely on an agent CLI not currently supported (e.g., Gemini CLI)
- you require a permissive license - it is AGPL-3.0

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, developer-tools, chat-interface, workflow-automation, terminal-ui
- domain: developer-tools, large-language-models, cross-platform
- platform: windows
- tags: ai-coding-agents, claude-code, codex, opencode, git-worktrees, keyboard-first, multi-agent-orchestration, playbooks, unattended-runs, ai-agents, automation, desktop, macos, linux, typescript

## Member repositories
- RunMaestro/Maestro (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:53.700023+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:22:56.379781+00:00, confidence not recorded.
  - readme: https://github.com/RunMaestro/Maestro (fetched 2026-08-28T04:07:53.700023+00:00, sha e42313af99e9)
  - homepage: https://RunMaestro.ai (fetched 2026-08-29T09:36:13.445194+00:00, sha 9dbfd47258bf)
  - site_page: https://docs.runmaestro.ai (fetched 2026-08-29T09:36:13.449843+00:00, sha 6fd8a9ff5835)
  - site_page: https://runmaestro.ai (fetched 2026-08-29T09:36:13.447925+00:00, sha 9dbfd47258bf)
- Data as of 2026-08-30T08:39:29.467469+00:00.