Automated README summary
Automatically summarized from the README on 30 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
mu is a TypeScript coding agent built on pi. It routes 40 bounded yes/no, choice and score decisions in the agent loop to a small judge model instead of the main model or fixed rules, cutting wasted tokens, autopilot approvals and half-finished runs.
How it uses Jev
Jev is the default judge, hosted by TypeSafe. At 40 decision points mu asks Jev bounded questions (e.g. does this tool output matter, is this command safe, did the run stop short) and uses the returned probabilities to admit context, gate commands, and send the agent back to finish. Verdicts are logged in a local ledger.
Primitives:choicescorenoul
Technique worth stealing
Route many small bounded decisions to a cheap judge model with calibrated probabilities, log every verdict, and allow shadow mode to compare judges before acting.
Try it
npm i -g mu-agent && mu setup && mu (Node.js 22.19+), or install the desktop app.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.15
- Shows a System One patternFound in material0.81
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.98
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.04
- Is a replica of the modelnot found in the excerpt0.20
- Solves a common problem (0–2)score on a 0–2 scale1.54 / 2
- About JevFound in material0.86
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 30 Oct 2026.