Skip to content
Sign in
  • Browse all toolsFilter by category and pricing
  • Browse categoriesWriting, code, image, audio and more
  • Compare toolsPut up to three side by side
  • Read the blogGuides and comparisons

OpenRig

Build persistent AI coding agent teams with shared context, roles and coordinated work.

OpenRig is an open-source agent orchestration system that turns AI coding agents into persistent teams with roles, shared context and coordinated work. OpenRig serves developers using Claude Code or Codex and is available under the Apache-2.0 license through guided setup or command-line installation.

Updated 9 Nov 20266 sections

OpenRig website screenshot

What is OpenRig?

OpenRig is an open-source system for building and running persistent networks of AI coding agents. OpenRig serves developers who want to organize coding agents as a team rather than manage separate terminal sessions. Teams have roles, shared context and owned work, with Claude Code and Codex supported together in the same rig.

OpenRig uses a lead-agent model: a developer describes the desired outcome, and the lead agent can coordinate specialists across teams. OpenRig brings results and decisions back for human attention. The repository describes starting with a repository and a useful change, then keeping the team's work and context at the same addresses.

What OpenRig can do

OpenRig combines team definitions, agent coordination and terminal-based visibility. OpenRig lets developers define an agent team in YAML and boot that team with a command. The system wraps coding-agent harnesses rather than replacing them, bringing supported agents into a shared operational structure with an operator and team dashboard.

  • OpenRig defines agent teams in YAML.
  • OpenRig coordinates specialists across teams through a lead agent.
  • OpenRig manages Claude Code and Codex in the same rig.
  • OpenRig maintains persistent teams with shared context and owned work.
  • OpenRig displays a team dashboard through rig tui.
  • OpenRig preserves existing conversations when reopening the operator view.

How OpenRig works

OpenRig offers a guided installation path through a rigs skill added to Claude Code or Codex inside a project folder. The developer invokes the skill and describes what should be built. The skill tells the developer what commands and changes are planned before installing OpenRig, opening the view and passing the goal to the operator.

OpenRig also supports manual installation of @openrig/cli through npm, followed by setup. The rig setup --dry-run command previews setup changes. OpenRig uses Herdr when installed and otherwise uses plain tmux for the operator layout. Developers can return to the operator by asking their coding agent to open OpenRig.

Who OpenRig is for

OpenRig is for developers already using terminal-based AI coding agents who want persistent coordination around a project. OpenRig can begin with either Claude Code or Codex; both accounts are not required. The documented workflow centers on describing a useful repository change, choosing a team and working through the operator.

  • OpenRig supports developers delegating repository changes to agent teams.
  • OpenRig supports users coordinating specialist agents across teams.
  • OpenRig supports developers keeping ongoing team work and context together.
  • OpenRig supports users managing Claude Code and Codex as a shared system.

OpenRig pricing and access

OpenRig is available as open-source software under the Apache-2.0 license. The repository provides guided installation and manual CLI installation instructions rather than a hosted pricing table. OpenRig requires a working Claude Code or Codex account, and the setup instructions explicitly say that a second subscription is not required.

OpenRig strengths and limitations

OpenRig combines persistent team organization with support for different coding-agent harnesses and a terminal dashboard. OpenRig also documents setup changes and provides a dry-run command. However, deployment requires local tools and provider sign-in, and setup affects configuration files and permissions. The repository recommends backing up affected files because preservation or rollback is not guaranteed.

  • OpenRig requires Node.js and tmux on macOS or Linux.
  • OpenRig supports Windows through WSL2, not native Windows.
  • OpenRig automated tests do not yet run on WSL2.
  • OpenRig gives the kernel broader permissions than project teams by default.
  • OpenRig setup can modify provider settings, tmux configuration and project guidance files.

OpenRig FAQ

What is OpenRig?

OpenRig is an open-source system for building and running persistent teams of AI coding agents. OpenRig organizes agents with roles, shared context and owned work, and lets a lead agent coordinate specialists across teams.

Is OpenRig open source?

OpenRig is open-source software distributed under the Apache-2.0 license. OpenRig can be installed through its guided coding-agent skill or through the CLI package, and requires a working Claude Code or Codex account.

Does OpenRig require both Claude Code and Codex?

OpenRig requires a working Claude Code or Codex account, not both. OpenRig can adapt the shipped starter team to the available provider, and the setup instructions state that a second subscription is not required.

Does OpenRig work on Windows?

OpenRig supports Windows through WSL2 and does not support native Windows. OpenRig also supports macOS and Linux, requires Node.js and tmux, and notes that its automated tests do not yet run on WSL2.

How do you install OpenRig?

OpenRig can be installed by adding its rigs skill to Claude Code or Codex and invoking that skill in a project folder. OpenRig also provides manual installation through npm and a rig setup --dry-run command to preview setup changes.

What configuration files does OpenRig change?

OpenRig setup can change tmux configuration, provider trust and hook settings, discovery skills and project guidance files. OpenRig does not guarantee preservation or rollback of these files, so the repository recommends making backups before setup.

From the community

No reviews yet

Be the first to review this tool. What you write helps the next person choose.

More tools like OpenRig

Ruflo

www.github.com

Open-source agent orchestration for Claude Code, Codex and MCP clients, with swarms, memory and workflow controls.

Free

Mysti

www.github.com

An open-source VS Code extension for coordinating coding agents, comparing answers and reviewing code.

Free

agent-teams-ai

www.github.com

Free desktop app for coordinating AI agent teams, tracking tasks, and reviewing code across multiple providers.

Free

Loom

www.github.com

An open-source delivery harness for planning, building, checking, and repairing work with coding agents.

Free