mco

Name: mco
Author: mco-org

bymco-org· 1 MCP server

Stars

465

Forks

How to install mco?

mco-org/mco

$git clone https://github.com/mco-org/mco

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install mco by running `git clone https://github.com/mco-org/mco`, then use it for the current task and follow its documentation at https://github.com/mco-org/mco.

Files · 1

View on GitHub

README.md

1	<p align="center">
2	<img src="https://raw.githubusercontent.com/mco-org/mco/main/docs/assets/brand/mco-cover-starry.jpg" alt="MCO — ten agent paths converging through a monumental M beneath a starry sky" width="100%" />
3	</p>
4
5	<h1 align="center">MCO</h1>
6
7	<p align="center"><strong>Orchestrate AI coding agents. Compare perspectives. Act with confidence.</strong></p>
8
9	<p align="center">
10	<a href="https://www.npmjs.com/package/@tt-a1i/mco"><img src="https://img.shields.io/npm/v/@tt-a1i/mco?style=flat-square&color=cb3837&logo=npm&logoColor=white" alt="npm version" /></a>
11	<a href="https://www.npmjs.com/package/@tt-a1i/mco"><img src="https://img.shields.io/npm/dm/@tt-a1i/mco?style=flat-square&color=cb3837" alt="npm downloads" /></a>
12	<a href="https://github.com/mco-org/mco/stargazers"><img src="https://img.shields.io/github/stars/mco-org/mco?style=flat-square&color=f59e0b" alt="GitHub stars" /></a>
13	<a href="./LICENSE"><img src="https://img.shields.io/badge/License-MIT-22c55e?style=flat-square" alt="MIT License" /></a>
14	<img src="https://img.shields.io/badge/Python-3.10%2B-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python 3.10+" />
15	</p>
16
17	<p align="center">English · <a href="./README.zh-CN.md">简体中文</a></p>
18
19	MCO is a lightweight, CLI-first orchestration layer for AI coding agents. Give one task to the agents and models you choose, run them in parallel, and compare their raw answers before you act.
20
21	Use MCO for code review, implementation, architecture analysis, CI checks, and any workflow where one model's blind spots matter.
22
23	It works from a terminal or from another coding agent such as Claude Code, Codex, Cursor, Copilot, Pi, or OpenClaw.
24
25	> MCO is actively maintained. For a browser workbench with persistent agent identity and a shared task graph, see [Hive](https://hivehq.dev).
26
27	## Quick start
28
29	Install the CLI and its bundled `mco-cli` Skill:
30
31	```bash
32	npx @tt-a1i/mco@latest install
33	```
34
35	Check the agents available on your machine:
36
37	```bash
38	mco doctor --json
39	```
40
41	Run a read-only multi-agent review:
42
43	```bash
44	mco review \
45	--repo . \
46	--prompt "Review this repository for high-risk bugs." \
47	--providers claude,codex,pi
48	```
49
50	Run a coding task with workspace write access:
51
52	```bash
53	mco run \
54	--repo . \
55	--prompt "Implement the requested change and run the relevant tests." \
56	--providers codex,pi \
57	--execution-mode write
58	```
59
60	MCO never silently chooses a provider/model team. If neither `--providers` nor `--agent` is supplied, ask the user which agents and models to use.
61
62	## Why MCO
63
64	One agent gives you one perspective. MCO turns selected agents into a review or execution team:
65
66	1. Choose — explicitly select the agents for the task.
67	2. Dispatch — run them in parallel, chain their work, or divide the scope.
68	3. Compare — retain each invocation's complete raw answer and operational status.
69	4. Decide — inspect evidence, disagreements, and failures before acting.
70
71	MCO keeps answer text opaque. It does not turn natural-language output into findings, severity, confidence, consensus, or an automatic decision.
72
73	For explicit review coordination, `--perspectives-json` adds a Provider-specific prompt focus. `--divide files` excludes ignored/local/build directories and round-robins the remaining sorted repository files without overlap, while `--divide dimensions` rotates review lenses in declaration order without changing target paths. These choices are visible in dry-run and arrange only the prompt or scope; the returned invocation answers remain raw.
74
75	## Built-in providers
76
77	\| Provider \| CLI \| Provider ID \|
78	\|----------\|-----\|-------------\|
79	\| Claude Code \| `claude` \| `claude` \|
80	\| Codex CLI \| `codex` \| `codex` \|
81	\| Gemini CLI \| `gemini` \| `gemini` \|
82	\| OpenCode \| `opencode` \| `opencode` \|
83	\| Qwen Code \| `qwen` \| `qwen` \|
84	\| GitHub Copilot CLI \| `copilot` \| `copilot` \|
85	\| Hermes \| `hermes` \| `hermes` \|
86	\| Pi \| `pi` \| `pi` \|
87	\| [Grok Build](https://docs.x.ai/build/overview) \| `grok` \| `grok` \|
88	\| [Cursor CLI](https://c

6 picks

Type

mco

bymco-org· 1 MCP server

Stars

465

Forks

How to install mco?

mco-org/mco

$git clone https://github.com/mco-org/mco

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install mco by running `git clone https://github.com/mco-org/mco`, then use it for the current task and follow its documentation at https://github.com/mco-org/mco.

Files · 1

View on GitHub

README.md

1	<p align="center">
2	<img src="https://raw.githubusercontent.com/mco-org/mco/main/docs/assets/brand/mco-cover-starry.jpg" alt="MCO — ten agent paths converging through a monumental M beneath a starry sky" width="100%" />
3	</p>
4
5	<h1 align="center">MCO</h1>
6
7	<p align="center"><strong>Orchestrate AI coding agents. Compare perspectives. Act with confidence.</strong></p>
8
9	<p align="center">
10	<a href="https://www.npmjs.com/package/@tt-a1i/mco"><img src="https://img.shields.io/npm/v/@tt-a1i/mco?style=flat-square&color=cb3837&logo=npm&logoColor=white" alt="npm version" /></a>
11	<a href="https://www.npmjs.com/package/@tt-a1i/mco"><img src="https://img.shields.io/npm/dm/@tt-a1i/mco?style=flat-square&color=cb3837" alt="npm downloads" /></a>
12	<a href="https://github.com/mco-org/mco/stargazers"><img src="https://img.shields.io/github/stars/mco-org/mco?style=flat-square&color=f59e0b" alt="GitHub stars" /></a>
13	<a href="./LICENSE"><img src="https://img.shields.io/badge/License-MIT-22c55e?style=flat-square" alt="MIT License" /></a>
14	<img src="https://img.shields.io/badge/Python-3.10%2B-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python 3.10+" />
15	</p>
16
17	<p align="center">English · <a href="./README.zh-CN.md">简体中文</a></p>
18
19	MCO is a lightweight, CLI-first orchestration layer for AI coding agents. Give one task to the agents and models you choose, run them in parallel, and compare their raw answers before you act.
20
21	Use MCO for code review, implementation, architecture analysis, CI checks, and any workflow where one model's blind spots matter.
22
23	It works from a terminal or from another coding agent such as Claude Code, Codex, Cursor, Copilot, Pi, or OpenClaw.
24
25	> MCO is actively maintained. For a browser workbench with persistent agent identity and a shared task graph, see [Hive](https://hivehq.dev).
26
27	## Quick start
28
29	Install the CLI and its bundled `mco-cli` Skill:
30
31	```bash
32	npx @tt-a1i/mco@latest install
33	```
34
35	Check the agents available on your machine:
36
37	```bash
38	mco doctor --json
39	```
40
41	Run a read-only multi-agent review:
42
43	```bash
44	mco review \
45	--repo . \
46	--prompt "Review this repository for high-risk bugs." \
47	--providers claude,codex,pi
48	```
49
50	Run a coding task with workspace write access:
51
52	```bash
53	mco run \
54	--repo . \
55	--prompt "Implement the requested change and run the relevant tests." \
56	--providers codex,pi \
57	--execution-mode write
58	```
59
60	MCO never silently chooses a provider/model team. If neither `--providers` nor `--agent` is supplied, ask the user which agents and models to use.
61
62	## Why MCO
63
64	One agent gives you one perspective. MCO turns selected agents into a review or execution team:
65
66	1. Choose — explicitly select the agents for the task.
67	2. Dispatch — run them in parallel, chain their work, or divide the scope.
68	3. Compare — retain each invocation's complete raw answer and operational status.
69	4. Decide — inspect evidence, disagreements, and failures before acting.
70
71	MCO keeps answer text opaque. It does not turn natural-language output into findings, severity, confidence, consensus, or an automatic decision.
72
73	For explicit review coordination, `--perspectives-json` adds a Provider-specific prompt focus. `--divide files` excludes ignored/local/build directories and round-robins the remaining sorted repository files without overlap, while `--divide dimensions` rotates review lenses in declaration order without changing target paths. These choices are visible in dry-run and arrange only the prompt or scope; the returned invocation answers remain raw.
74
75	## Built-in providers
76
77	\| Provider \| CLI \| Provider ID \|
78	\|----------\|-----\|-------------\|
79	\| Claude Code \| `claude` \| `claude` \|
80	\| Codex CLI \| `codex` \| `codex` \|
81	\| Gemini CLI \| `gemini` \| `gemini` \|
82	\| OpenCode \| `opencode` \| `opencode` \|
83	\| Qwen Code \| `qwen` \| `qwen` \|
84	\| GitHub Copilot CLI \| `copilot` \| `copilot` \|
85	\| Hermes \| `hermes` \| `hermes` \|
86	\| Pi \| `pi` \| `pi` \|
87	\| [Grok Build](https://docs.x.ai/build/overview) \| `grok` \| `grok` \|
88	\| [Cursor CLI](https://c

6 picks

Type

mco

How to install mco?

Related

mco

How to install mco?

Related