Jev in production › Search, ranking and matching

jev-assist

Coding-agent skill and CLI that takes piped candidates such as grep hits or file lists and asks Jev a noul, choice or score question per line, returning them sorted with a cut line so the agent reads only the rows above it.

Open on GitHub ↗

The source publishes no measured number.
Use
Search, ranking and matching
Industry
Developer tools
Form
Open-source tool
Stage
In production
Plugs into
coding-agent skills (skills.sh)
Listed
2026-09-21
Found via
discord
Repository
glud123/jev-assist
Stars
4
Forks
1
Last push
2026-09-24
Language
JavaScript
License
MIT

The README opens with

A search comes back as hundreds of lines: too many to read, too risky to guess at. Pipe the candidates in — raw grep -rn, git ls-files, a test run, no reformatting — and each one comes back with a calibrated number, sorted, with an exact total and a cut line. The reply is ~30 rows whether the pool was 40 or 4,000. Built on the three typed judgments of TypeSafe Jev: noul (is this hit real?), choice (what is it?), score (how bad is it?).

Search tells you where a hit is; this tells you what each hit is. Finding things stays with grep/rg/Glob — nothing here searches, by design.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for search, ranking and matching