# awslabs/cli-agent-orchestrator

Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions

Repository: https://github.com/awslabs/cli-agent-orchestrator
Canonical: https://ross.abutalabs.com/products/cli-agent-orchestrator
Homepage: https://awslabs.github.io/cli-agent-orchestrator/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent-orchestration, ai-agents, ai-coding-assistant, antigravity, claude-code, codex, copilot-cli, cursor-cli, developer-tools, hermes, kimi-cli, kiro, mcp, model-context-protocol, multi-agent-systems, opencode, orchestration, python, tmux
Last push: 2026-09-02T23:05:53+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 99, longevity 28
- inputs: {"age_days": 400, "days_push": 0, "days_rel": 5, "gap_med": 9.5, "n_releases_24m": 15}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1195, forks 251 (observed 2026-09-03T02:15:09.445271+00:00)

## What it is
CLI Agent Orchestrator (CAO) is a Python tool that coordinates multiple AI coding CLIs (Claude Code, Kiro, Codex, Copilot CLI, Cursor CLI, and others) by running them in isolated tmux sessions under a supervisor agent. It exposes orchestration via an MCP server, supports scheduled multi-agent pipelines, and includes a real-time web dashboard.

## Use cases
- orchestrate multiple AI coding agents in parallel
- delegate coding tasks from a supervisor agent to specialist workers
- run multi-agent AI pipelines on a schedule
- mix different AI CLI providers in one workflow
- monitor AI agent sessions from a web dashboard
- expose agent orchestration to MCP-compatible clients

## When to choose
- you use several AI coding CLIs and want them coordinated in one workflow
- you want a supervisor agent delegating tasks to parallel worker agents locally
- you need scheduled, cron-like multi-agent automation
- you want MCP-native agent orchestration with zero cloud infrastructure

## When to avoid
- you need a single-agent coding assistant only
- you require cloud-hosted or distributed agent orchestration
- you cannot install tmux or run local terminal sessions
- your provider CLI is not among the supported list

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, mcp, cli, workflow-automation, scheduling
- domain: developer-tools
- platform: python, cli
- tags: multi-agent, tmux, claude-code, codex, kiro, orchestration, ai-coding-assistants, supervisor-agent, ai-agents, automation, command-line, linux, macos

## Member repositories
- awslabs/cli-agent-orchestrator (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:09.445271+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:36:56.018989+00:00, confidence not recorded.
  - readme: https://github.com/awslabs/cli-agent-orchestrator (fetched 2026-09-03T02:15:09.445271+00:00, sha 26e763e1dd3a)
  - homepage: https://awslabs.github.io/cli-agent-orchestrator/ (fetched 2026-08-29T12:42:04.728025+00:00, sha 0ae67aab358f)
  - registry_pypi: https://pypi.org/pypi/cli-agent-orchestrator/json (fetched 2026-08-29T12:42:04.734368+00:00, sha f16792f5c173)
- Data as of 2026-08-30T08:39:29.467469+00:00.