Back to agent tooling
jevr project preview
Agent tooling

jevr

Semantic code and document search CLI for coding agents: a stateless BM25 pass recalls candidate files, Jev Nouls verify each one window-by-window against the query, and one listwise Choice reranks the survivors into grep-style path:line output with calibrated relevance scores.

Semantic code and document search CLI — BM25 recall + TypeSafe Jev calibrated precision

How it uses Jev

Find files and content using Jev's calibrated decisions.

Highlights

  • Query in plain language. "how does crash recovery work?" beats
  • Calibrated scores, not keyword hits. Every result carries a relevance
  • Grep-honest exit codes. 0 matches, 1 none above threshold, 2
  • Code and documents in one tool , verified by separate calibrated
  • No repository state. The BM25 index is rebuilt per invocation
  • Measured, not vibed. Defaults are benchmark-derived operating points —

Getting started

Requires Rust 1.88+ and a TypeSafe API key.

Languages
Rust 92% · Python 6% · Shell 2%
License
Apache-2.0
Latest release
jevr 0.1.1
Last activity
Sep 2026
Added
2026-09-23
Stars at snapshot
0
Status
Community listing
bm25claude-codeclicode-searchcoding-agentsdeveloper-tools

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Listed in Jev Library

If this is your project, the badge below links back to this page. Paste it near the top of your README.

[![Listed in Jev Library](https://jevlibrary.dev/api/badge/romeromarcelo-jev-retrieval)](https://jevlibrary.dev/projects/romeromarcelo-jev-retrieval)

Something wrong on this page, or would you rather not be listed? Tell us and it will be changed.