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.
Agent-agnostic (Claude Code, Codex, Aider) · Runtime-agnostic (tmux, Docker) · Tracker-agnostic (GitHub, Linear)
# Install
git clone https://github.com/ComposioHQ/agent-orchestrator.git
cd agent-orchestrator && bash scripts/setup.sh
# Configure your project
cd ~/your-project && ao init --auto
# Launch and spawn an agent
ao start
ao spawn my-project 123 # GitHub issue, Linear ticket, or ad-hocDashboard opens at http://localhost:3000. Run ao status for the CLI view.
ao spawn my-project 123
- Workspace creates an isolated git worktree with a feature branch
- Runtime starts a tmux session (or Docker container)
- Agent launches Claude Code (or Codex, or Aider) with issue context
- Agent works autonomously — reads code, writes tests, creates PR
- Reactions auto-handle CI failures and review comments
- Notifier pings you only when judgment is needed
Eight slots. Every abstraction is swappable.
| Slot | Default | Alternatives |
|---|---|---|
| Runtime | tmux | docker, k8s, process |
| Agent | claude-code | codex, aider, opencode |
| Workspace | worktree | clone |
| Tracker | github | linear |
| SCM | github | — |
| Notifier | desktop | slack, composio, webhook |
| Terminal | iterm2 | web |
| Lifecycle | core | — |
All interfaces defined in packages/core/src/types.ts. A plugin implements one interface and exports a PluginModule. That's it.
# agent-orchestrator.yaml
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: notifyCI 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.
ao status # Overview of all sessions
ao spawn <project> [issue] # Spawn an agent
ao send <session> "Fix the tests" # Send instructions
ao session ls # List sessions
ao session kill <session> # Kill a session
ao session restore <session> # Revive a crashed agent
ao dashboard # Open web dashboardRunning 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 spawn and walk away. The system handles isolation, feedback routing, and status tracking. You review PRs and make decisions — the rest is automated.
- Node.js 20+
- Git 2.25+
- tmux (for default runtime)
ghCLI (for GitHub integration)
pnpm install && pnpm build # Install and build all packages
pnpm test # Run tests (3,288 test cases)
pnpm dev # Start web dashboard dev serverSee CLAUDE.md for code conventions and architecture details.
| Doc | What it covers |
|---|---|
| Setup Guide | Detailed installation and configuration |
| Examples | Config templates (GitHub, Linear, multi-project, auto-merge) |
| CLAUDE.md | Architecture, conventions, plugin pattern |
| Troubleshooting | Common issues and fixes |
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 CLAUDE.md for the pattern.
MIT