Jev in production › Search, ranking and matching

jegrep

Semantic grep CLI where Jev returns a calibrated yes/no probability per file for a natural-language query, then reports matching files and line ranges with no index. $0.01–0.03 per search over a few thousand files (author).

Open on GitHub ↗

$0.01–0.03measured, as published by the source
Use
Search, ranking and matching
Industry
Developer tools
Form
Open-source tool
Stage
In production
Listed
2026-09-20
Found via
github
Repository
can1357/jegrep
Stars
115
Forks
10
Last push
2026-09-26
Language
Rust
License
MIT

The README opens with

Natural-language search that works like grep. No embeddings, no index, no daemon.

- Semantic: Finds concepts ("where do we verify JWT tokens?"), not just strings. - No Index: Searches the live tree on every run. Nothing to build, refresh, or go stale. - Calibrated: Every path gets an absolute yes/no probability, so thresholds mean something and batches stay comparable. - Precise: Returns files and line ranges as dirname/filename:first-last references, ready to paste into an editor, with original line numbers and merged adjacent passages. - Cheap: Jev bills $0.042 per million input tokens, output free. A typical search over a few thousand files runs ~$0.005. - Agent-Ready: --json for scripts and coding agents, --compact for a token-lean digest,...

Badge

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

Listed in Jev in production

Also used for search, ranking and matching