dzhng/jevgrep
Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.
About the project
A CLI for coding agents that finds relevant files and source excerpts in a repository from a question about code behavior. It uses Jev for relevance ranking and requires a Vercel AI Gateway, TypeSafe, or OpenRouter key.
Useful for
- Find files where authentication is checked before a request handler
- Install the agent skill for Claude Code or Codex via jg skill
- Check provider and key configuration with jg doctor
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 123 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 1 day old and already has 130 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #93.
- About 50 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 130
- Today
- 0 · ≈ 123 by evening
- Forks
- 8
- Issues and pull requests
- 1
- Watchers
- 0
- Language
- TypeScript
- License
- MIT
- Latest release
- v0.1.0 · September 26, 2026
- Created
- September 26, 2026
- Last push
- September 26, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 27, 2026Top new repositories this week: #93
- September 26, 2026Top new repositories this week: #188
Similar by description
-
0.7
nassim-arifette/jevgrep
Semantic code search tool for coding agents: finds code by behavior across a repository via CLI or MCP, returning exact source excerpts with paths and line numbers.
-
1.0
can1357/jegrep
A command-line tool for semantic code search: given a natural-language description, it finds files and line ranges using an LLM instead of embeddings or an index. Works like grep, but by meaning.