Getting Started

OpenRig is a multi-agent harness, a local control plane that manages your Claude Code and Codex sessions as a single system. Define your agent teams in YAML, manage them from one CLI.

What OpenRig Does

You say “I want a dev pair (implementer + QA), an orchestrator, and a review team.” OpenRig creates the tmux sessions, launches the agents, gives them their role-specific instructions, connects them to each other, and shows the whole topology in a browser-based operator view. When something breaks, OpenRig snapshots and restores the entire topology.

# The product loop
down (auto-snapshot) → up <rig-name> (auto-restore) → work → repeat

# Boot a topology
rig up my-rig.yaml

# Check node status
rig ps --nodes

# Shut down (auto-snapshots first)
rig down <rigId>

# Restore from name (finds latest snapshot)
rig up my-rig
Workflow pair
The product loop in one screenshot

OpenRig's lifecycle is easier to understand when the teardown handoff and restore path are shown together.

1. rig down <rigId> --snapshot2. rig up <rig-name>
workflow pair showing rig down with snapshot followed by restore-by-name rig up

Two Users, Always Together

The Human

Directs the work. Decides what to build, which agents to spin up, when to snapshot. Watches the operator view. Steps in when something needs a judgment call.

The Coding Agent

Drives the CLI. Runs rig up,rig ps,rig restore. Reads error messages, adapts, retries. The CLI is designed for this user - a 10x staff engineer at the terminal.

The relationship: Human directs agent. Agent drives CLI/UI. System is honest to both levels - the agent needs accurate error messages, the human needs accurate dashboard state.

Core Concepts

What Ships In The Library

The spec library is part of the product surface, not just a folder on disk. Operators can inspect what ships with OpenRig, preview a topology, and boot from proven examples instead of starting every rig from scratch.

That makes the CLI documentation useful for both onboarding and reuse: you can point an agent at the library and tell it to start from an existing pattern.

CLI proof
Spec library inventory

Browse reusable rigs and agents directly from the terminal.

rig specs ls output showing the shipped OpenRig spec library

Install

# Install OpenRig CLI
npm install -g @openrig/cli

# Start the daemon
rig daemon start

# Open the UI
rig ui open

# Verify the local install
rig doctor

The daemon runs locally, manages state in SQLite, and provides the HTTP API that the CLI, UI, and MCP tools all consume.

CLI proof
Install health check

`rig doctor` is the fastest way to confirm that local prerequisites are actually in place.

rig doctor output showing install health checks passing

Product Vocabulary

A handful of words name the things you work with day to day. The first group is the topology: what a rig is made of and how you run it. The second group is the coordination layer: how a fleet of agents passes work around without losing it. These are first-class product surfaces, not internal plumbing; the Taxonomy page defines the full set.

Topology
rig - a multi-agent topology
agent - one harnessed coding agent
pod - a bounded context group inside a rig
node - one running agent within a rig
snapshot - a point-in-time capture of a rig
up / down - boot a rig / tear it down (auto-snapshots)
Coordination
queue item - one unit of owned work
handoff - passing work, transactionally
workflow - a durable sequence of work
chatroom - durable rig-scoped messaging
context pack - a bundle that primes an agent
watchdog - a daemon-native scheduler

Where To Go Next