Log inSubmit server
Cli Agent Orchestrator logo

Cli Agent Orchestrator

Coordinates multiple AI coding CLIs through a supervisor, using isolated tmux sessions for parallel or sequential work.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Cli Agent Orchestrator

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "cli-agent-orchestrator": {
      "command": "uvx",
      "args": [
        "--from",
        "cli-agent-orchestrator",
        "cao-mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

cli-agent-orchestrator MCP server coordinates multiple AI coding CLIs through a supervisor and isolated local tmux sessions. It runs a local `cao-server`, launches provider CLIs as full native processes, and gives the supervisor coordination tools for parallel or sequential delegation. Supported providers include Claude Code, Kiro CLI, Codex CLI, Cursor CLI, and others. Reach for it when a coding task benefits from specialist agents working across a shared project workflow.

Use cases

  • Delegate coding tasks to specialist CLIs
  • Run coding agents in parallel tmux sessions
  • Sequence multi-step implementation workflows
  • Observe agent sessions through the web UI
  • Coordinate agents across isolated project worktrees

Key features

  • Supervisor-driven multi-agent coordination
  • Isolated tmux sessions for provider CLIs
  • Parallel and sequential task delegation
  • Support for multiple authenticated coding CLIs
  • Shell CLI, web UI, and operations MCP control planes
  • Agent profiles, workflows, skills, and persistent memory

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 1h ago via OSV.dev · cli-agent-orchestrator (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1.5kStargazers on the source repository.
Last commitTodayMost recent push to the default branch.

How Cli Agent Orchestrator works

What cli-agent-orchestrator does

cli-agent-orchestrator coordinates AI coding command-line tools under the direction of a supervisor. Instead of replacing each provider's CLI, it starts those CLIs as ordinary processes and preserves their native authentication and capabilities. Workers run in isolated tmux sessions, allowing a supervisor to assign work to multiple agents at once or arrange tasks into a sequence.

The project fits the Coding Agents category and provides several control surfaces around the local orchestration runtime, including a shell CLI, a web interface, an operations MCP server, and plugins. It also includes support for flows, workflows, agent profiles, skills, memory, and optional self-learning features.

How it works

The runtime is built around a local cao-server. A typical session has the server running in one terminal, while a second terminal launches a supervisor from the project directory. CAO then starts the selected provider CLIs in separate tmux sessions. Operators can watch the attached launch terminal, use the web UI at http://localhost:9889, or attach to the relevant tmux session.

The built-in code_supervisor profile provides a starting point for supervisor-driven work. Sessions can be stopped individually by name or shut down together with the all-sessions command. Agent profiles can select providers and define overrides, while tool restrictions can apply roles, allowlists, and provider enforcement.

Setup and configuration

CAO requires Python 3.11 or newer, tmux 3.3 or newer, and uv. At least one supported provider CLI must be installed and authenticated before CAO starts. Providers listed by the project include Kiro CLI, Claude Code, Codex CLI, Antigravity CLI, Hermes, Kimi CLI, MiniMax Code, GitHub Copilot CLI, OpenCode CLI, Oh My Pi, Cursor CLI, and Grok Build CLI.

Install the main branch as a uv tool with:

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

After installation, install the supervisor profile, start the server, and launch it from the target project:

bash
cao install code_supervisor
cao-server
cao launch --agents code_supervisor

Provider-specific guides cover installation, authentication, and provider overrides. CAO can also be installed from PyPI or through its devcontainer feature. The cao update command updates an existing installation.

Tools and capabilities

The supervisor can coordinate workers in parallel or sequence and can use the operations MCP server as a control plane. Other available control surfaces include:

  • A shell CLI for launching, updating, and shutting down sessions
  • A web UI for observing and operating the agent fleet
  • MCP Apps for browser or host-rendered interfaces
  • Flows and workflows for scheduled or multi-step runs
  • Reusable skills with installation, discovery, loading, updating, and removal
  • Persistent cross-session memory and an opt-in self-learning loop
  • Agent and event plugin support, with agent plugins gated off by default
  • HTTP API and PTY WebSocket routes for API and terminal streaming use cases

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Cli Agent Orchestrator

cli-agent-orchestrator is an MCP server that connects a supervisor to local AI coding CLIs running in isolated tmux sessions. Its coordination tools let the supervisor delegate work to multiple agents in parallel or sequence while those agents retain their native CLI authentication and capabilities.

Install it as a uv tool with `uv tool install git+https://github.com/awslabs/cli-agent-orchestrator.git@main --upgrade`. You need Python 3.11+, tmux 3.3+, uv, and at least one authenticated provider CLI. PyPI and a devcontainer feature are also available installation paths.

It supports Kiro CLI, Claude Code, Codex CLI, Antigravity CLI, Hermes, Kimi CLI, MiniMax Code, GitHub Copilot CLI, OpenCode CLI, Oh My Pi, Cursor CLI, and Grok Build CLI. A provider must be installed and authenticated before launching CAO.

Install the `code_supervisor` profile, start `cao-server`, and run `cao launch --agents code_supervisor` from the target project directory. You can observe the session in the launch terminal, through the web UI at `http://localhost:9889`, or by attaching to its tmux session.

Yes, Cursor CLI is one of the supported provider CLIs. Install and authenticate Cursor CLI before starting CAO, then follow its provider-specific guide if you need to select it instead of the default Kiro CLI provider.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewCli Agent Orchestrator AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/cli-agent-orchestrator?style=directory)](https://allmcps.com/mcp/cli-agent-orchestrator)
HTML Embed
<a href="https://allmcps.com/mcp/cli-agent-orchestrator"><img src="https://allmcps.com/api/badge/cli-agent-orchestrator?style=directory" alt="Cli Agent Orchestrator on AllMCPs" /></a>