AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
openrig
openrig logo

openrig

Active·★ 8.3k·Apache-2.0·Updated 2026-10-27

OpenRig's framing is that a harness wraps a model and a rig wraps your harnesses. It turns a pile of terminal coding sessions into a persistent, organized team defined in YAML and booted with one command, with Claude Code, Codex and Pi managed as one system. You talk to a lead agent about the outcome you want, and it coordinates specialists across teams and brings back results and decisions that need you.

The suggested setup is to add the rigs skill to Claude Code or Codex with npx skills add, then type /rigs or $rigs; the skill tells you what it will run and change, installs OpenRig and hands your goal to its kernel operator, which adapts a starter team to whichever provider you have. A TUI shows the rig as a graph or as a table of seats with runtime, model, context and state.

It requires Node.js 22 or 24, tmux, macOS or Linux (WSL2 on Windows) and a signed-in Claude Code or Codex. The README is explicit about what it changes: it adds a block to ~/.tmux.conf, writes hooks and trust settings for Codex and Claude Code, installs discovery skills, and adds guidance to AGENTS.md or CLAUDE.md. By default the kernel gets broad permissions, including full access without approval prompts on Codex, which a permission policy can tighten. Apache-2.0 licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-27.

License
Apache-2.0
Latest release
v0.7.4 · 2026-10-27
Last commit
2026-10-27
Contributors
84
Forks
677
Open issues and PRs
131
First published
2026-04-01
npm package
@openrig/cli 0.7.4 · 3,814 downloads last week

Source: GitHub, npm and PyPI public APIs.

#agent-team#agent-orchestration#claude-code#codex#tmux#yaml#cli
$ Install
$ npx skills add https://github.com/mvschwarz/openrig/tree/v0.7.0/skills/rigs --skill rigs --agent claude-code
↗ Visit site★ GitHub
01

Features

01Agent teams defined in YAML and started with one command
02Claude Code, Codex and Pi in the same rig
03Kernel operator agent that adapts a starter team to your provider
04TUI showing seats with runtime, model, context and state
05Installable as a rigs skill in Claude Code or Codex
02

Why choose it

+One YAML file and one command bring up a whole team of coding agents.
+Claude Code and Codex run side by side under one lead agent.
+The README lists every change it makes to your machine and config.
03

Trade-offs

!The kernel runs with broad permissions by default, including no approval prompts on Codex.
!Modifies tmux, Claude Code and Codex config and project instruction files.
!No native Windows; needs tmux and a specific Node.js version.
04

Maintenance check

ActiveChecked: 2026-10-26
Last commit
2026-10-26
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v0.7.2 (2026-10-25)
Open issues
129
Recent issues with at least one comment
0/3

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #1813 OpenRig 0.6.10: daemon event-loop hangs (up to 14 min), outbox rows never leave "pending", queue accepts rows for non-existent sessions24 comments · 2026-10-23
  • #331 Stall checks miss unsubmitted wakes and flag waiting or working seats21 comments · 2026-10-01
  • #161 Daemon event loop saturates at scale: per-seat tmux polling (transcripts, structural, identity) spawns ~300 processes/s; transcript config l16 comments · 2026-09-29
  • #81 Seats blocked on a permission prompt (needs_input) don't raise rig attention or any watchdog alert16 comments · 2026-09-27
  • #88 Windows Support14 comments · 2026-09-27

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

macOS / Linux / WSL2
CLI + tmux
Verified via docs
Claude Code
Harness
Verified via docs
Codex
Harness
Verified via docs
06

Quick start

1
$ npx skills add https://github.com/mvschwarz/openrig/tree/v0.7.0/skills/rigs --skill rigs --agent claude-code
07

Use cases

↳Run a persistent team of coding agents on a repository
↳Have a lead agent coordinate specialists toward one outcome
↳Combine Claude Code and Codex in one managed system
08

Alternatives

⚡Top VS:
VSpaperclip★108.0k→VSagent-orchestrator★13.8k→VSclaw-orchestrator★601→VSkungfu★4.5k→
paperclip logo
paperclip★ 108.0k
The open-source app everyone uses to manage agents at work
VSCompare→
agent-orchestrator logo
agent-orchestrator★ 13.8k
Open-source (Apache-2.0) orchestrator for Claude Code, Codex & 30+ coding agents. Plan, run and supervise agent teams from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps.
VSCompare→
claw-orchestrator logo
claw-orchestrator★ 601
Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.
VSCompare→
kungfu logo
kungfu★ 4.5k
Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.
VSCompare→
takt logo
takt★ 1.4k
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML
VSCompare→
open-duet logo
open-duet★ 6.2k
Open-source, self-hosted alternative to Claude Duet: AI coworkers (named agents) with instructions, memory, routines, their own isolated computer, and your approval before they act. Also an alternative to OpenAI Dots, Meta Muse, Grok Bot, Manus Cue and ChatGPT agent.
VSCompare→
Orkas logo
Orkas★ 2.2k
Orkas is an open-source, local-first AI desktop app: a commander LLM directs specialist sub-agents, and runs your installed coding CLIs — Claude Code, Codex, OpenCode, OpenClaw, Hermes — as local sessions. Agents self-evolve via reflection and skill crystallization. BYO keys. macOS / Windows / Linux.
VSCompare→
agmsg logo
agmsg★ 1.6k
Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
mvschwarz /
openrig
↗

Define a persistent team of Claude Code and Codex agents in YAML and boot it with one command

8.3k677Apache-2.0
Last commit1d ago
StatusActive
CategoryMulti-Agent
Contributors84
Latest releasev0.7.4
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.