mco-org/mco

CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.

What it solves

MCO addresses the problem of "single-agent blind spots" in AI-assisted coding. Instead of relying on one AI model's perspective, it allows developers to orchestrate multiple coding agents in parallel to compare their raw answers, identify disagreements, and make more confident decisions during code reviews, implementations, or architecture analysis.

How it works

MCO acts as a CLI-first orchestration layer that sits between the user (or another AI agent) and various coding agent CLIs (such as Claude Code, Codex, and Gemini). It uses a shared adapter contract to detect, run, poll, and cancel provider processes. When a task is dispatched, MCO runs the selected agents in parallel or in a chain, collects their raw outputs (text, JSON, or Markdown artifacts), and presents them for comparison without automatically synthesizing a final decision, ensuring the user retains full control.

Who it’s for

It is designed for developers who use AI coding agents and want to verify the accuracy of AI-generated code or reviews by comparing multiple models, as well as for other AI agents that need a tool to dispatch tasks to a team of specialized coding agents.

Highlights

  • Multi-Agent Orchestration: Run multiple providers (e.g., Claude, Codex, Pi) in parallel or chained sequences.
  • Coded-First Interface: Lightweight CLI designed for terminal use or integration into other agents like Cursor or Copilot.
  • Flexible Execution Modes: Supports read_only for reviews and write for workspace mutations.
  • Raw Answer Preservation: Maintains the complete raw output of each invocation to avoid losing nuance during synthesis.
  • Broad Provider Support: Built-in adapters for a wide range of tools including Claude Code, Gemini, Qwen Code, and Grok Build.

Related

  • Project
    awslabs/cli-agent-orchestrator

    CLI Agent Orchestrator (CAO) is a Python tool that lets you run several AI‑coding command‑line interfaces (like Claude Code, Copilot CLI, etc.) as coordinated agents. It starts a local server, launches each provider CLI in its own tmux pane, and offers a web UI, API, and plugin system for building parallel or sequential code‑generation pipelines.

  • Project
    code-yeongyu/oh-my-openagent

    An AI agent command-line tool that automates complex professional workflows like coding and deep research using multi-agent graphs and a persistent memory system.

  • Project
    Get-Concord-AI/concord-mcp

    Concord MCP is an open‑source, local‑first coordination layer that lets multiple AI coding assistants (Claude Code, Codex, Cursor, Gemini CLI, Grok Build, Goose, GitHub Copilot CLI, etc.) share a common work‑state. It provides a tiny MCP server backed by SQLite, a set of tools (`start_work`, `inspect_work`, `update_work`, `transfer_work`, `finish_work`) and a CLI (`concord status`, `dashboard`, `check`, …) so agents can claim files, detect overlaps before editing, exchange prompts/replies, hand off tasks, and generate review packets. Setup is a single `npm install -g @concord-ai/concord-mcp && concord setup`. The project is MIT‑licensed and sends optional anonymous telemetry.

  • Project
    zts212653/clowder-ai

    Clowder AI is a platform layer that turns isolated AI coding agents into a collaborative team, giving them persistent identities, shared memory, cross-model review, and agent-to-agent messaging so you don't have to manually route copy-paste context.