📦awslabs / cli-agent-orchestrator
← 返回首页
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
⚖️ Apache-2.0#agent-orchestration#ai-agents#ai-coding-assistant#antigravity#claude-code🌐 awslabs.github.io📅 创建于 2025-07-29🔄 更新于 2026-11-20
🔗 GitHub Python
本站解读

面向 AI 编码命令行工具的多 agent 编排层,把 Claude Code、Kiro、Codex 等代理放进各自隔离的 tmux 会话,由 supervisor 将任务分派给专职 agent,避免多个代理挤在同一终端里互相干扰。缩写 CAO 在文档中反复出现,指的就是这套协调机制:supervisor 负责拆解与汇总,specialist 只处理被指派的子任务。Python 编写,Apache-2.0 许可。文档有中英双语,README 开头专门解释了横幅图片为何只用浅色——那种深蓝在深色主题下对比度仅 1.77:1,与其跟随主题切换,不如固定成一种。适合已经在同时使用多个编码 CLI、靠手动切换和复制粘贴维持协作的人。仓库另有一份中文 README 与英文版同步。

上榜 2 天 · 首次上榜 2026-11-20 · 近 7 天 +10 star · 榜单最高 #14 · Apache-2.0

📄 仓库 README

在 GitHub 查看 ↗
来自 GitHub 仓库自述文件 · 版权归原作者所有

CLI Agent Orchestrator (CAO)

English | 简体中文

PyPI version Python versions Ask DeepWiki

CLI Agent Orchestrator (CAO) coordinates multiple AI coding CLIs so a supervisor can delegate work to specialist agents in parallel or sequence.

📚 Documentation — guides, reference, and two interactive courses.

What CAO does

CAO runs a local cao-server, starts provider CLIs in isolated terminal sessions, and gives a supervisor tools for coordinating workers. The agents remain full CLI processes with their native authentication and capabilities. See CODEBASE.md for the runtime architecture and package layout.

Prerequisites

Install:

The focused provider guides contain installation, authentication, and provider-specific behavior.

Install CAO

Install the current main branch as a uv tool:

uv tool install git+https://github.com/awslabs/cli-agent-orchestrator.git@main --upgrade
cao --help

For a tagged release, install cli-agent-orchestrator from PyPI. See DEVELOPMENT.md for a source checkout. For container-based installation, see the devcontainer feature.

To update an existing CAO installation:

cao update

See Updating CAO for source-aware behavior and edge cases.

First supervisor launch

The unqualified commands below use CAO's default Kiro CLI provider. If you installed a different provider, follow its focused guide above for the provider override while keeping the same sequence.

  1. Install the built-in supervisor profile:

bash cao install code_supervisor

  1. In terminal A, start the local server and leave it running:

bash cao-server

  1. In terminal B, change to the project directory the agents should work in, then launch the supervisor:

bash cd /path/to/your/project cao launch --agents code_supervisor

  1. Observe the supervisor in the attached launch terminal, open the Web UI at http://localhost:9889, or follow the tmux guide to attach to its session.

  2. Stop the named session when finished:

bash cao shutdown --session {session-name}

To stop every CAO session instead, run cao shutdown --all.

Where to go next

Operate CAO

  • Control-plane selection: choose the Web UI, shell CLI, operations MCP server, or plugins.
  • Web UI and MCP Apps: browser and host-rendered fleet interfaces.
  • Kiro Crew: see, steer, start, and stop CAO sessions from the Kiro Crew dashboard with the CAO Shelf App, and remote control a session from a Kiro Crew chat.
  • Flows and workflows: scheduled runs and multi-step pipelines.
  • Launch decisions: local routing settings and content-free records.
  • Skills: install, scope, and author reusable agent guidance.
  • Skills lifecycle example: install, discover, load, apply, update, and remove a reusable skill in an isolated home.
  • Memory and self-learning: persistent cross-session memory, and the opt-in loop that turns workflow outcomes into lessons and promoted instructions.
  • AI-DLC portfolio example: coordinate parallel AI-DLC intents across repositories and isolated worktrees.
  • Cross-zone robot transport: coordinate simulated transport, measured custody handoffs, and independent checks.
  • Hierarchical robot factory: a supervisor and three team-manager agents run nine Open Duck Mini robots on a simulated make, assemble, and ship line, and balance its bottleneck.
  • Self-hosted decision model: run the open JevK5-4B decision model locally or on AWS (CDK), behind a loopback-only /v1/systemone API.
  • Tool restrictions: roles, allowlists, and provider enforcement.
  • Kubernetes deployment: run a supervisor and worker fleet on Amazon EKS, with shared workspace, per-pod state, and credential delivery.
  • Updating CAO: update an installed uv tool.

Configure and integrate

Contribute

Contributing

See CONTRIBUTING.md and DEVELOPMENT.md before submitting changes. Documentation changes must also follow the documentation maintenance rule.

License

This project is licensed under the Apache License 2.0. See LICENSE.

📈 近 7 天 Star 趋势

每日新增 Star(柱)与累计 Star(线)· 数据来自 GitHub

🏆 排名变化趋势

在各榜单中的排名历史(数字越小越靠前)

📋 历史上榜记录

每次快照的详细数据
日期 榜单 排名 周期新增 总 STAR