Agent Orchestrator — The Orchestration Layer for Parallel AI Agents

Spawn parallel AI coding agents, each in its own git worktree. Agents autonomously fix CI failures, address review comments, and open PRs — you supervise from one dashboard.

Agent Orchestrator manages fleets of AI coding agents working in parallel on your codebase. Each agent gets its own git worktree, its own branch, and its own PR. When CI fails, the agent fixes it. When reviewers leave comments, the agent addresses them. You only get pulled in when human judgment is needed.

See it in action

Prerequisites: Node.js 20+, Git 2.25+, tmux, gh CLI. Install tmux via brew install tmux (macOS) or sudo apt install tmux (Linux).

npm install -g @aoagents/ao

git clone https://github.com/ComposioHQ/agent-orchestrator.git
cd agent-orchestrator && bash scripts/setup.sh

Point it at any repo — it clones, configures, and launches the dashboard in one command:

ao start https://github.com/your-org/your-repo

Or from inside an existing local repo:

cd ~/your-project && ao start

That's it. The dashboard opens at http://localhost:3000 and the orchestrator agent starts managing your project.

ao start ~/path/to/another-repo

1. You start — ao start launches the dashboard and an orchestrator agent
2. Orchestrator spawns workers — each issue gets its own agent in an isolated git worktree
3. Agents work autonomously — they read code, write tests, create PRs
4. Reactions handle feedback — CI failures and review comments are automatically routed back to the agent
5. You review and merge — you only get pulled in when human judgment is needed

The orchestrator agent uses the AO CLI internally to manage sessions. You don't need to learn or use the CLI — the dashboard and orchestrator handle everything.

ao start auto-generates agent-orchestrator.yaml with sensible defaults. You can edit it afterwards to customize behavior:

# agent-orchestrator.yaml
# Runtime data is auto-derived under ~/.agent-orchestrator/{hash}-{projectId}/
port: 3000

defaults:
  runtime: tmux
  agent: claude-code
  workspace: worktree
  notifiers: [desktop]

projects:
  my-app:
    repo: owner/my-app
    path: ~/my-app
    defaultBranch: main
    sessionPrefix: app

reactions:
  ci-failed:
    auto: true
    action: send-to-agent
    retries: 2
  changes-requested:
    auto: true
    action: send-to-agent
    escalateAfter: 30m
  approved-and-green:
    auto: false # flip to true for auto-merge
    action: notify

CI fails → agent gets the logs and fixes it. Reviewer requests changes → agent addresses them. PR approved with green CI → you get a notification to merge.

See agent-orchestrator.yaml.example for the full reference, or run ao config-help for the complete schema.

AO keeps your Mac awake while running, so you can access the dashboard remotely (e.g., via Tailscale from your phone) without the machine going to sleep.

How it works: On macOS, AO automatically holds an idle-sleep prevention assertion using caffeinate. When AO exits, the assertion is released.

# agent-orchestrator.yaml
power:
  preventIdleSleep: true  # Default on macOS, no-op on Linux

Set to false if you want to allow idle sleep while AO runs.

Lid-close limitation: macOS enforces lid-close sleep at the hardware level — no userspace assertion can override it. If you need remote access while traveling with the lid closed, use clamshell mode (external power + display + input device).

Seven plugin slots. Lifecycle stays in core.

All interfaces defined in packages/core/src/types.ts. A plugin implements one interface and exports a PluginModule. That's it.

Running one AI agent in a terminal is easy. Running 30 across different issues, branches, and PRs is a coordination problem.

Without orchestration, you manually: create branches, start agents, check if they're stuck, read CI failures, forward review comments, track which PRs are ready to merge, clean up when done.

With Agent Orchestrator, you: ao start and walk away. The system handles isolation, feedback routing, and status tracking. You review PRs and make decisions — the rest is automated.

pnpm install && pnpm build    # Install and build all packages
pnpm test                      # Run tests (3,288 test cases)
pnpm dev                       # Start web dashboard dev server

See docs/DEVELOPMENT.md for code conventions and architecture details.

Contributions welcome. The plugin system makes it straightforward to add support for new agents, runtimes, trackers, and notification channels. Every plugin is an implementation of a TypeScript interface — see CONTRIBUTING.md and the Development Guide for the pattern.

MIT