jevbooks

← All projects

jgrep

keltokhy/jgrep

grep where the pattern is a plain-English description.

What it is

jgrep filters text lines, structured records, functions, and diff hunks against plain-English descriptions. It is for developers and analysts who want semantic filtering in a pipe, on logs, files, CSVs, JSONL, patches, or code.

How it uses Jev

Each line, record, function, or diff hunk becomes one yes/no question to Jev, TypeSafe's decision model. Jev returns a probability in about 200 ms for about a thousandth of a cent. jgrep judges concurrently and prints matches in input order.

Primitives:noul

Technique worth stealing

Judge each line as one yes/no question to a decision model, then filter by probability threshold.

Try it

uv tool install jev-grep, set TYPESAFE_API_KEY, then jgrep "a complaint about noise" complaints.txt

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricyes0.95
  • Shows a System One patternyes0.73
  • Handles uncertaintyno0.06
  • Measuredunclear0.48
  • Runnableyes0.83
  • Worth recommendingunclear0.43
  • Model replicano0.04
  • Problem scopescore on a 0–2 scale1.30
  • About Jevyes0.98

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 21 Sept 2026.