mu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.
Last commit November 3, 2026, 8 days ago.
572 GitHub stars and 0 Honeystax upvotes. Copy the install, test the workflow, then decide if it earns a permanent slot.
Reasonable to try, but it will take more than a quick skim to get real signal.
Starts at 6. Added: GitHub health not measured +10, no security policy +8, no contributing guide +4, no code of conduct +3.
AI Agent
Universal
Model
Multiple
Fastest way to find out if mu belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
git clone https://github.com/qybaihe/mu ~/.claude/agents/mu-2Run this first. You will know quickly if the workflow earns a permanent slot.
rm -rf ~/.claude/agents/mu-2No messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ skills/ ├─ agents/ │ └─ mu-2/ ← installs here └─ settings.json
mu is listed on Honeystax as an Agent for Universal, since October 6, 2026. Its code is at github.com/qybaihe/mu, with 572 GitHub stars. Last commit November 3, 2026, 8 days ago.
Source: GitHub repository
Source check: November 3, 2026
Upstream commit: November 3, 2026
Repository state: Not marked archived
Honeystax upvotes are community interest signals, not star ratings. GitHub stars and repository health are source measurements; editorial risk and trial-cost notes are Honeystax analysis.