{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "qybaihe/mu",
 "name": "mu",
 "owner": "qybaihe",
 "slug": "qybaihe-mu",
 "github": "https://github.com/qybaihe/mu",
 "what": "mu is a command line and desktop coding agent that sends routine permission and context decisions to a small judge model so the main model can focus on the code.",
 "why": "",
 "language": "TypeScript",
 "requirements": [
  "Node.js 22.19 or newer for the command line, or the desktop installer for macOS, Windows or Linux",
  "An API key or a supported ChatGPT, Claude, Grok or Google subscription (the free Jev on OpenCode Zen answers until you set a judge key)",
  "A project folder to work in"
 ],
 "audience_note": "Developers who use an AI coding agent and want fewer permission prompts, with an audit trail of each judge decision.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/qybaihe-mu/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "qybaihe-mu--run-judged-coding-session",
   "title": "Run a coding session that asks only about risky steps",
   "best": true,
   "url": "https://dedupedai.com/use-cases/qybaihe-mu/run-judged-coding-session/",
   "json": "https://dedupedai.com/use-cases/u/qybaihe-mu/run-judged-coding-session.json"
  },
  {
   "id": "qybaihe-mu--compare-judge-in-shadow-mode",
   "title": "Compare a judge in shadow mode before trusting it",
   "best": false,
   "url": "https://dedupedai.com/use-cases/qybaihe-mu/compare-judge-in-shadow-mode/",
   "json": "https://dedupedai.com/use-cases/u/qybaihe-mu/compare-judge-in-shadow-mode.json"
  },
  {
   "id": "qybaihe-mu--code-with-desktop-app-no-terminal",
   "title": "Code with the Mu desktop app and no terminal",
   "best": false,
   "url": "https://dedupedai.com/use-cases/qybaihe-mu/code-with-desktop-app-no-terminal/",
   "json": "https://dedupedai.com/use-cases/u/qybaihe-mu/code-with-desktop-app-no-terminal.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}