Repo · Coding & code review

mu

A coding agent where a small judge makes the routine calls.

Open github.com ↗

From the repository

mu (μ): a coding agent that thinks before it acts. A small, fast judge makes the routine calls, the big model does the work. Built on pi and AionUi.

agent-harnessai-agentai-codingaionuiclicoding-agentcontext-engineeringdesktop-appdeveloper-toolselectronjevllmmulti-agentpi-coding-agentprompt-injectiontypesafetypescript

How builders describe it

Mu (μ): a coding agent that thinks before it acts. A small, fast judge makes the routine calls, the big model does the work. Built on pi and AionUi.

Early-stage coding agent built on pi (CLI + desktop app) with a judgment kernel: Jev answers typed questions at decision points such as tool approval, constraint checks, context admission and test-log trimming, each switchable active/shadow/off and logged to a verdict ledger.

A coding agent built on pi that hands its non-code decisions — what enters the context, whether a command is safe, whether the work is done — to a small judge model at 35 decision points per turn.

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →

Related projects