cli-agent-orchestrator

cli-agent-orchestrator

Multi-agent orchestration tool that coordinates multiple AI coding CLI tools running in isolated tmux sessions.

MCPDevOpen source
Type
MCP
Transport
http
Open source
Yes
GitHub Stars
★ 1.0k
Source
mcp-github

Overview

CLI Agent Orchestrator (CAO) is a multi-agent orchestration tool designed to coordinate multiple AI coding CLI tools (such as Claude Code, Kiro, Codex, etc.), enabling supervisors to delegate tasks either in parallel or sequentially to specialized agents. CAO runs a local `cao-server`, which launches provider CLIs within isolated terminal sessions and provides supervisory tools for coordination. These agents maintain their full CLI processes along with native authentication and capabilities. Ideal for developers who need to use multiple AI coding tools simultaneously.

Capabilities

  • Coordinate multiple AI coding CLI tools
  • Run in isolated tmux sessions
  • Support various AI coding tools
  • Provide Web UI and MCP Apps interface

Use cases

Parallel processing of multiple AI coding tasksAutomated code generation and optimizationCross-project code managementIntegration with multiple AI coding tools

Setup

Requires: Python 3.10或更高版本tmux 3.3或更高版本uv至少一个支持的提供者CLI
Install uv tool: `uv tool install git+https://github.com/awslabs/cli-agent-orchestrator.git@main --upgrade`; or install from PyPI: `pip install cli-agent-orchestrator`.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How do I update CAO?

Run the `cao update` command to update your existing installation.

Which AI coding CLI tools are supported?

Supports Kiro CLI, Claude Code, Codex CLI, and other tools.

Related skills