DEDUPED Hot AI repos, turned into use cases Get the Monday 5
105 stars · TypeScript

How to use Jevgrep: what you can do with it

What is Jevgrep? JevGrep is a TypeScript tool that finds code by behavior, sending eligible source fragments to a configured AI provider for scoring and returning exact excerpts with paths and line numbers, via a CLI or a local MCP server.

How do I use it? Run npm install -g @nassim-arifette/jevgrep; then run jevgrep init --global; run cd path/to/my-project and then jevgrep init, answering y only after you have reviewed the scope. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Find where a behavior lives in an unfamiliar repo

    Ask a plain question about behavior and get exact code excerpts with line numbers.

    View prompt
    Using the JevGrep CLI in the repository at <repo path>, run `jevgrep search --query "<behavior question>"` and list each returned excerpt with its path and line range. Verify that the result reports complete coverage before treating an empty or short result as meaningful.

  • Give Claude Code or Codex a semantic search tool

    Connect an agent to one authorized repository through the semantic_search_code MCP tool.

    View prompt
    Confirm that the jevgrep MCP server for the repository at <repo path> lists the semantic_search_code tool, then call it with the question "<behavior question>" and report the returned excerpts with their paths and line numbers. Verify that the tool call completes and that any partial or incomplete coverage is stated in your report.

  • Review what leaves the machine before a first search

    Check the eligible scope, limits and provider setup without any network request.

    View prompt
    In the repository at <repo path>, run `jevgrep doctor` and `jevgrep inspect` and summarize the eligible file count, the exclusions and the provider in use. Verify that no search command has been run and that remote evaluation is disabled until a person approves it.

  • Run scoped searches that return JSON for scripts

    Limit a search to chosen folders and read a validated JSON result with exit codes.

    View prompt
    Run `jevgrep search --query "<behavior question>" --scope <folder> --json` in the repository at <repo path> and parse the JSON output. Verify that you check the exit code and report whether the result is complete or partial before drawing any conclusion.

Quick start with Jevgrep

  1. Check you have what it needs: Node.js 24; npm; An API key for TypeSafe AI, Vercel AI Gateway or OpenRouter.
  2. Open nassim-arifette/jevgrep on GitHub and read the README and license.
  3. Run npm install -g @nassim-arifette/jevgrep
  4. Run jevgrep init --global
  5. Run cd path/to/my-project and then jevgrep init, answering y only after you have reviewed the scope
  6. Run jevgrep inspect to confirm which files are eligible and what is excluded

These steps come from our top use case, Find where a behavior lives in an unfamiliar repo, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for nassim-arifette/jevgrep

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Jevgrep alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and coding agents working in unfamiliar or large repositories who do not know the file name or symbol they need.
  • Why it is hot105 stars, launched 36 days ago
  • LanguageTypeScript
  • Sourcegithub.com/nassim-arifette/jevgrep · Back to Hot repos

Requirements

  • Node.js 24
  • npm
  • An API key for TypeSafe AI, Vercel AI Gateway or OpenRouter
  • Permission to send eligible source excerpts from the target repository to the chosen provider

Add this badge to your README

Maintain Jevgrep? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/nassim-arifette/jevgrep.svg)](https://dedupedai.com/use-cases/nassim-arifette-jevgrep/?utm_source=github&utm_medium=badge&utm_campaign=nassim-arifette-jevgrep)

HTML 

<a href="https://dedupedai.com/use-cases/nassim-arifette-jevgrep/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=nassim-arifette-jevgrep"><img src="https://dedupedai.com/badge/nassim-arifette/jevgrep.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Jevgrep

What is Jevgrep?

JevGrep is a TypeScript tool that finds code by behavior, sending eligible source fragments to a configured AI provider for scoring and returning exact excerpts with paths and line numbers, via a CLI or a local MCP server. It is an open-source project on GitHub: https://github.com/nassim-arifette/jevgrep.

How do I use Jevgrep?

Run npm install -g @nassim-arifette/jevgrep; then run jevgrep init --global; run cd path/to/my-project and then jevgrep init, answering y only after you have reviewed the scope. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Jevgrep for?

Developers and coding agents working in unfamiliar or large repositories who do not know the file name or symbol they need.

What can I do with Jevgrep?

4 use cases so far, for example: Find where a behavior lives in an unfamiliar repo; Give Claude Code or Codex a semantic search tool; Review what leaves the machine before a first search. Each has steps and a copy-paste agent prompt.

What do I need to run Jevgrep?

Node.js 24; npm; An API key for TypeSafe AI, Vercel AI Gateway or OpenRouter; Permission to send eligible source excerpts from the target repository to the chosen provider.

What are alternatives to Jevgrep?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Jevgrep safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.