jevgrep is a command-line code discovery tool designed to help AI coding agents understand unfamiliar repositories faster. Users ask a question about what a codebase does instead of manually crafting text or symbol searches. The tool evaluates folders, files, and declarations with Jev to identify likely relevant areas. Its response includes file suggestions, reading leads, and verbatim source excerpts in one stdout result. An accompanying Agent Skill teaches tools such as Claude Code, Codex, and OpenCode how to use the CLI effectively. It works on macOS, Linux, and Windows with Node.js 22 or newer. Several model gateways are supported, including Vercel AI Gateway, OpenRouter, OpenCode Zen, and compatible custom endpoints.

Features

  • Natural-language codebase search
  • Jev-powered relevance scoring
  • Relevant file and declaration discovery
  • Verbatim source context output
  • Agent Skill installation
  • Multiple model gateway providers

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow jevgrep

jevgrep Web Site

Other Useful Business Software
Build Agents and Models on One Platform Icon
Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of jevgrep!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

TypeScript

Related Categories

TypeScript Command Line Tools

Registered

2 days ago