StackMap
Subscribe
Explore / jevgrep
dzhng

jevgrep

Find code by asking what it does: `jg` uses the Jev decision model to judge folders, files and declarations, returning relevant files plus verbatim excerpts for coding agents. CLI + skill.

2,586 189 TypeScript MITupdated 9 days ago
code-intelcoding
View on GitHubDispute this mapping →
Curator's take

Use it when your agent lands in an unfamiliar repo and burns turns grepping for where a behavior lives — no index to build, and measured ~26% lower total cost at the same solve rate on its own 10-task SWE-bench run. Skip it when you already know the symbol or path (plain `rg` wins), or when you want zero per-query spend: every search is a paid Jev call through Vercel AI Gateway, TypeSafe, OpenRouter or a compatible endpoint. Install the skill too, or agents won't call it.

Mapped by ShipWithAI editors · links verified

Continue your stack

What teams reach for next — and why each earns a place beside jevgrep. Ranked by curator confidence.

alternativealternativealternativecocoindex-codezvec-greptokensavejevgrep
pairs wellalternativebuilt withpick a node for the why · open it from the panel
Weekly digest
README.md2 min read

jevgrep — Same intelligence. About 30% lower cost.

jevgrep

npm MIT license Node.js 22+ Release

Same intelligence. ~30% lower cost.

Find code by asking what it does. In our ten-task SWE-bench comparison, Jevgrep successfully completed the same 8 of 10 tasks as the baseline, at lower cost.

Coding agents spend part of every unfamiliar task finding the right files. Jevgrep gives them a place to start: ask a repository question, and jg returns relevant files, reading leads, and verbatim source excerpts in one stdout response. It uses Jev to judge relevance across folders, files, and declarations. Your coding agent then implements and tests the change.

npm install -g @dzhng/jevgrep
jg auth
jg skill
jg "How are telemetry events recorded and sent?" ./my-project

Requires Node.js 22+, macOS, Linux, or Windows, and a key for Vercel AI Gateway, TypeSafe, OpenRouter, OpenCode Zen, or a custom TypeSafe-compatible endpoint. No separate Python, Bun, or ripgrep installation is required to use jg.

Provider selection requires 0.3.0 or newer. Upgrade an older installation with npm install --global @dzhng/jevgrep@latest.

Install the agent skill — required for agent setup

Installing the CLI alone does not teach your coding agent to use it. Install the skill as well, from the project where your agent works:

jg skill

The installer detects your coding agents (Claude Code, Codex, OpenCode and others) and asks where to install. Add --global for a user-wide install, or --yes for unattended installation. The skill explains installation, invocation and the meaning of returned context. It leaves research and implementation decisions to the calling agent. The current repository skill checks for jg and installs the CLI if it is missing; authentication still needs your selected provider’s key. The skill installer itself does not configure credentials.

jg skill delegates to the skills CLI and needs npm/npx plus network access. You can also run that installer directly, without the CLI installed:

npx skills add dzhng/jevgrep --skill jevgrep

In 0.1.0, jg skill only prints the bundled skill; use npx skills with that version.

Upgrade

There is currently no jg upgrade command. Upgrade the CLI with npm:

npm install -g @dzhng/jevgrep@latest
jg --version

Update the installed skill separately by rerunning jg skill. Updating the npm package does not overwrite skill files in your projects. See the package guide for authentication details.

Start with a question, leave with source

Use jg when you know the behavior you need to understand but not where it lives:

jg "Where is authentication checked before a request reaches a handler?" .
jg "How are database connections created, pooled, and closed?" ./src
jg "Which tests cover retry behavior when a request times out?" .

Jevgrep explores the repository hierarchy and follows qualifying branches. It selects files using content previews, then identifies useful source units and surrounding context. It keeps qualifying file locations even when it cannot confidently return an excerpt; it does not force every search into a fixed top-two list.

The summary and compact file list come first, followed by selected source with line references, then detailed declaration and call locations.