WorkflowsMay 13, 2026·2 min read

Maestro — Multi-Agent Orchestration for Coding CLIs

Maestro is an Apache-2.0 multi-agent orchestrator with 39 specialists for Gemini CLI, Claude Code, Codex, and Qwen Code, plus review/debug entrypoints.

Agent Toolkit
Agent Toolkit · Community
Agent ready

Safe staging for this asset

This asset is staged first. The copied prompt tells the agent to inspect the staged files and ask before activating scripts, MCP config, or global config.

Stage only · 17/100Policy: stage
Agent surface
Any MCP/CLI agent
Kind
CLI Tool
Install
Stage only
Trust
Trust: Established
Entrypoint
Asset
Safe staging command
npx -y tokrepo@latest install 87fa0169-9e32-591a-8eb0-3c90ca91322e --target codex

Stages files first; activation requires review of the staged README and plan.

Intro

Maestro is an Apache-2.0 multi-agent orchestrator with 39 specialists for Gemini CLI, Claude Code, Codex, and Qwen Code, plus review/debug entrypoints.

Best for: teams standardizing multi-agent workflows across different coding CLIs and runtime surfaces

Works with: Node.js 20+, Gemini CLI / Claude Code / Codex / Qwen Code, plugin/extension hooks

Setup time: 10-18 minutes

Key facts (verified)

  • GitHub: 409 stars · 26 forks · pushed 2026-05-02.
  • License: Apache-2.0 · owner avatar + repo URL verified via GitHub API.
  • README-verified entrypoint: git clone https://github.com/josstei/maestro-orchestrate.git && cd maestro-orchestrate.

Main

  • Use Maestro when you want consistent roles and phases across tools—especially if your team mixes multiple coding CLIs.

  • Start with the “express” path for simple work, then adopt the 4-phase workflow once you need repeatable review and debugging lanes.

  • Treat specialists as contracts: define what each agent outputs (diffs, checklists, risk notes) so the team can automate handoffs.

Source-backed notes

  • README describes 39 specialists and a standard workflow for medium/complex work.
  • README lists multiple runtime targets: Gemini CLI, Claude Code, Codex, and Qwen Code with plugin/extension surfaces.
  • Repo is Apache-2.0 licensed and actively maintained.

FAQ

  • Is it tied to one runtime?: No—README documents surfaces for Gemini CLI, Claude Code, Codex, and Qwen Code.
  • How many specialists are included?: README claims 39 specialists.
  • What should I adopt first?: Start with a small subset (review/debug) before enabling many agents in parallel.
🙏

Source & Thanks

Source: https://github.com/josstei/maestro-orchestrate > License: Apache-2.0 > GitHub stars: 409 · forks: 26

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

CrewAI Flows — Event-Driven Multi-Agent Orchestration

CrewAI Flows is the event-driven orchestration layer on top of Crews. Decorators @start, @listen, @router build a typed state machine for multi-agent.

Workflows
CrewAI

Obsidian Agent Client — Bring Agents into Obsidian

Obsidian Agent Client adds ACP-based agent integrations (Claude Code/Codex/Gemini) to Obsidian; install via BRAT or Releases and use adapters (2,016★).

Workflows
Agent Toolkit

PraisonAI — Multi-Agent AI Orchestration Framework

PraisonAI is a production-ready framework for building autonomous AI agent workflows. It combines multi-agent orchestration with built-in memory, RAG, and tool use, supporting 100+ LLM providers in as few as five lines of code.

Skills
Script Depot

LLxprt Code — Multi-Provider AI Coding CLI

LLxprt Code is an open-source AI coding CLI that switches across providers (Anthropic, Gemini, Codex, local). Install via brew or npm.

CLI Tools
Script Depot
◈Home🔍Search👤Me