# CLI Agent Orchestrator: Multi-Agent Orchestration for AI Coding CLIs

This repository profile is provided by osrepos.com, an open source repository discovery platform.

Source: osrepos.com
Repository profile: https://osrepos.com/repo/awslabs-cli-agent-orchestrator
Generated for open source discovery and AI-assisted research.

The CLI Agent Orchestrator (CAO) is a powerful tool designed to coordinate multiple AI coding CLIs, enabling a supervisor to delegate tasks to specialist agents in parallel or sequence. It achieves this by running a local `cao-server` and launching provider CLIs within isolated tmux terminal sessions. This setup allows for efficient management and orchestration of various AI coding assistants.

GitHub: https://github.com/awslabs/cli-agent-orchestrator
OSRepos URL: https://osrepos.com/repo/awslabs-cli-agent-orchestrator

## Summary

The CLI Agent Orchestrator (CAO) is a powerful tool designed to coordinate multiple AI coding CLIs, enabling a supervisor to delegate tasks to specialist agents in parallel or sequence. It achieves this by running a local `cao-server` and launching provider CLIs within isolated tmux terminal sessions. This setup allows for efficient management and orchestration of various AI coding assistants.

## Topics

- AI Agents
- Agent Orchestration
- Multi-Agent Systems
- AI Coding
- Developer Tools
- Python
- Tmux
- Automation

## Repository Information

Last analyzed by OSRepos: Mon Aug 24 2026 16:03:26 GMT+0100 (Western European Summer Time)
Detail views: 3
GitHub clicks: 1

## Safety Notice

OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything.

## Content

## Introduction

The CLI Agent Orchestrator (CAO) is an innovative project from AWS Labs that streamlines the use of multiple AI coding Command Line Interfaces (CLIs). It acts as a central coordinator, allowing a supervisor to delegate work to various specialist agents, such as Claude Code, Kiro, Codex, and others, either in parallel or sequentially. CAO ensures that each agent operates in its own isolated tmux session, maintaining native authentication and capabilities while providing a unified orchestration layer.

This system is designed to enhance developer productivity by enabling complex coding tasks to be broken down and assigned to the most suitable AI agent, all managed from a single control plane.

## Installation

To get started with CLI Agent Orchestrator, ensure you meet the prerequisites and follow the installation steps:

### Prerequisites

*   Python 3.10 or later
*   tmux 3.3 or later
*   [uv](https://docs.astral.sh/uv/) (a fast Python package installer and resolver)
*   At least one supported provider CLI, authenticated before launching CAO. Examples include Kiro CLI, Claude Code, Codex CLI, GitHub Copilot CLI, and more.

### Install CAO

Install the current `main` branch as a `uv` tool:

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


To update an existing CAO installation:

bash
cao update


## Examples

Here's a quick guide to launching your first supervisor with CAO, using the default Kiro CLI provider:

1.  **Install the built-in supervisor profile:**

    bash
    cao install code_supervisor
    

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

    bash
    cao-server
    

3.  **In terminal B, navigate to your project directory and launch the supervisor:**

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

4.  **Observe the supervisor:** You can monitor its activity in the attached launch terminal, open the [Web UI](https://awslabs.github.io/cli-agent-orchestrator/docs/web-ui.html) at `http://localhost:9889`, or attach to its tmux session.

5.  **Stop the session when finished:**

    bash
    cao shutdown --session {session-name}
    

    To stop all CAO sessions, run `cao shutdown --all`.

## Why Use It

CLI Agent Orchestrator offers significant advantages for developers working with AI coding tools:

*   **Multi-Agent Coordination:** Seamlessly manage and coordinate multiple AI coding CLIs, allowing you to leverage the strengths of different models for various tasks.
*   **Isolated Environments:** Each agent operates in its own tmux session, ensuring isolation and preventing conflicts, while maintaining native CLI functionality.
*   **Enhanced Productivity:** Delegate complex coding tasks, automate workflows, and improve efficiency by orchestrating specialist AI agents.
*   **Flexible Control Planes:** Interact with CAO via a Web UI, shell CLI, or operations MCP server, providing options for different user preferences and integration needs.
*   **Advanced Features:** Benefit from features like flows, workflows, skills, persistent memory, and self-learning capabilities that allow agents to improve over time.
*   **Extensibility:** Support for plugins and a well-documented API allow for custom integrations and extensions.

## Links

*   **GitHub Repository:** [https://github.com/awslabs/cli-agent-orchestrator](https://github.com/awslabs/cli-agent-orchestrator){:target="_blank"}
*   **Official Documentation:** [https://awslabs.github.io/cli-agent-orchestrator/](https://awslabs.github.io/cli-agent-orchestrator/){:target="_blank"}
*   **PyPI Package:** [https://pypi.org/project/cli-agent-orchestrator/](https://pypi.org/project/cli-agent-orchestrator/){:target="_blank"}