[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:openrig":3},"\u003Ch1>OpenRig\u003C\u002Fh1>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@openrig\u002Fcli\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@openrig\u002Fcli\" alt=\"npm version\" \u002F>\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@openrig\u002Fcli\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdw\u002F@openrig\u002Fcli\" alt=\"npm downloads\" \u002F>\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fmvschwarz\u002Fopenrig\" alt=\"License: Apache 2.0\" \u002F>\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmvschwarz\u002Fopenrig?style=social\" alt=\"GitHub stars\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>A harness wraps a model. A rig wraps your harnesses. Define your agent team in YAML, boot it with one command. Claude Code and Codex in the same rig, managed as one system.\u003C\u002Fp>\n\u003Cp>OpenRig is open-source software for building and running your own network of agents. It turns AI coding agents from a pile of terminal sessions into a persistent, organized team. Talk to a lead agent about the outcome you want; it can coordinate specialists across teams and bring you results and decisions that need your attention. Start with a repository and one useful change, then keep the team's work and context at the same addresses.\u003C\u002Fp>\n\u003Cp>It's the open-source system behind my AI civilization experiments.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Guide:\u003C\u002Fstrong> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Fblob\u002FHEAD\u002Fdocs\u002Freference\u002Fquickstart.md\" rel=\"nofollow ugc noopener\">Getting started\u003C\u002Fa> · \u003Cstrong>Stuck?\u003C\u002Fstrong> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Fblob\u002FHEAD\u002Fdocs\u002Freference\u002Fhelp.md\" rel=\"nofollow ugc noopener\">Help\u003C\u002Fa> · \u003Cstrong>Questions:\u003C\u002Fstrong> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Fdiscussions\u002F92\" rel=\"nofollow ugc noopener\">Q&A\u003C\u002Fa> · \u003Cstrong>Updates and demos:\u003C\u002Fstrong> \u003Ca href=\"https:\u002F\u002Fx.com\u002F_feralmachine\" rel=\"nofollow ugc noopener\">@_feralmachine on X\u003C\u002Fa>\u003C\u002Fp>\n\u003Ch2>See it running\u003C\u002Fh2>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fmvschwarz\u002Fopenrig\u002FHEAD\u002Fassets\u002Freadme\u002Fopenrig-agents-working.gif\" alt=\"The OpenRig TUI: the build rig as a graph, then as a table of seats with runtime, model, context and state, then one seat in detail (real recording, 10 seconds)\" \u002F>\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Start here:\u003C\u002Fstrong> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Fblob\u002FHEAD\u002Fdocs\u002Freference\u002Fquickstart.md\" rel=\"nofollow ugc noopener\">the guided first-use path\u003C\u002Fa>: install, talk to the kernel operator, then choose a team for your first useful change.\u003C\u002Fp>\n\u003Cp>Not setting this up today? Get the next walkthrough and occasional OpenRig updates → \u003Ca href=\"https:\u002F\u002Fopenrig.dev\u002Ffollow\" rel=\"nofollow ugc noopener\">https:\u002F\u002Fopenrig.dev\u002Ffollow\u003C\u002Fa>\u003C\u002Fp>\n\u003Ch2>Install and first run\u003C\u002Fh2>\n\u003Cp>\u003Cstrong>Let your coding agent set it up.\u003C\u002Fstrong> First check that \u003Ccode>node --version\u003C\u002Fcode> shows 22 or 24: the command below needs\nNode.js and the \u003Ccode>npx\u003C\u002Fcode> that comes with it. Then, in your project folder, add OpenRig's \u003Ccode>rigs\u003C\u002Fcode> skill to the agent you\nuse:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-sh\"># Claude Code\nnpx skills add https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Ftree\u002Fv0.7.5\u002Fskills\u002Frigs --skill rigs --agent claude-code\n# Codex\nnpx skills add https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Ftree\u002Fv0.7.5\u002Fskills\u002Frigs --skill rigs --agent codex\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Then type \u003Ccode>\u002Frigs\u003C\u002Fcode> in Claude Code, or \u003Ccode>$rigs\u003C\u002Fcode> in Codex, and say what you want built. The skill has your agent tell\nyou what it will run and change before it does, install OpenRig, open the OpenRig view and pass your goal to\nOpenRig's operator.\u003C\u002Fp>\n\u003Cp>You need Node.js 22 or 24 (22 on Apple silicon), tmux, macOS or Linux (WSL2 on Windows), and Claude Code or Codex\nsigned in. One provider is enough to start.\u003C\u002Fp>\n\u003Cp>Already have OpenRig? Use the tag that matches \u003Ccode>rig --version\u003C\u002Fcode>, or upgrade first.\u003C\u002Fp>\n\u003Cp>Prefer to type the commands yourself? \u003Ca href=\"#install-it-yourself\" rel=\"nofollow ugc noopener\">Install it yourself ↓\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>Requires Node.js 22 or 24 and tmux, on macOS or Linux, and one working Claude Code or Codex account: one is enough, since the kernel operator adapts the shipped \u003Ccode>starter\u003C\u002Fcode> team to whichever you have. On Linux, the distribution's own Node.js can be older (Ubuntu 24.04's is 18); install a supported version with \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fnvm-sh\u002Fnvm\" rel=\"nofollow ugc noopener\">nvm\u003C\u002Fa> (\u003Ccode>nvm install 22\u003C\u002Fcode>) or NodeSource. On a Mac with Apple silicon, use Node.js 22 (\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig\u002Fblob\u002FHEAD\u002Fdocs\u002Freleases\u002Fv0.5.15.md#known-compatibility-limitation\" rel=\"nofollow ugc noopener\">compatibility history\u003C\u002Fa>). On a Mac where you aren't an administrator, or where Homebrew belongs to another account (its \u003Ccode>brew install\u003C\u002Fcode> is refused), install Node.js in your own home folder with \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fnvm-sh\u002Fnvm\" rel=\"nofollow ugc noopener\">nvm\u003C\u002Fa>: run \u003Ccode>touch ~\u002F.zshrc\u003C\u002Fcode> (a new Mac account has none, and nvm's installer only adds itself to a profile file that already exists), then nvm's install command, for nvm v0.40.8 \u003Ccode>curl -o- https:\u002F\u002Fraw.githubusercontent.com\u002Fnvm-sh\u002Fnvm\u002Fv0.40.8\u002Finstall.sh | bash\u003C\u002Fcode> (\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fnvm-sh\u002Fnvm#install--update-script\" rel=\"nofollow ugc noopener\">nvm's page\u003C\u002Fa>\u003C\u002Fp>\n",1793926097000]