jevgrep (dzhng)
Project / 项目 · In the catalogue / 在目录中查看
What Jev decides here · Jev 在这里做什么决定
Search & ranking (检索与排序), Context compaction (上下文压缩)
noul: read in the code by a model, not yet by a person 由模型在代码里读到，尚无人复核
a model read the call site; no person yet 模型读过调用点，尚无人复核 · · Cited file / 引用的文件: packages/core/test-node/provider-protocol.mjs
Summary · 摘要
CLI and agent skill that finds code by asking what it does: `jg "How are telemetry events recorded?" ./repo` has Jev judge relevance across folders, files and declarations and returns files and verbatim excerpts. The author reports the same 8 of 10 SWE-bench tasks solved at ~30% lower cost.written by a model
一个命令行工具和 Agent 技能，用“这段代码做什么”来找代码：`jg "遥测事件是如何记录的？" ./repo` 让 Jev 在目录、文件和声明层面判断相关性，返回相关文件、阅读线索和原文摘录。作者报告在 10 个 SWE-bench 任务上同样解决 8 个，成本约低 30%。模型撰写机翻
Notes · 备注
The cited file is the provider-protocol test, which pins the request each provider receives. Row drafted from the discovery queue (issue #14) by an AI assistant that read the README and the cited file on 2026-10-24; a maintainer has not yet read the call site.
所引文件是提供商协议测试，固定了每个提供商收到的请求内容。本条目由 AI 助手根据发现队列（issue #14）起草，于 2026-10-24 阅读了 README 和所引文件；维护者尚未亲自阅读调用点。
Launches · 发布记录
Not launched yet. 还没有发布过。 Launch it / 发布它 ↗ · How a product launches / 怎样发布一个产品
Makers · Maker
Made this? Confirm or correct its entry / 这是你做的？确认或更正条目 ↗
The same form takes the product's one line and a demo link, in its maker's own words. 同一个表单也可以补上产品的一句话和演示链接，用 Maker 自己的话。
Badge for its README · README 徽章
[](https://kydlikebtc.github.io/awesome-jev/products/jevgrep-dzhng.html)One line for the product's README, linked to this page. The picture says that it is listed; while it is on the launch board, that it is launching; after a week in the top three, its place. It is rebuilt with the site, so the line never needs changing. 放进产品 README 的一行，链接到本页。图片显示已收录；在发布榜上时显示正在发布；进过某周前三后显示名次。它随网站一起重建，这一行不用再改。
Also under this pattern · 同一模式的其他产品
AutoGPT TypeSafe blocks
Seven production blocks — choice, score, yes/no, ask-many, route, pick-best, filter — with a UTF-8 byte budget, verbatim wire capture and eleven test files.
OpenViking: retrieval reranking
One Noul per candidate document in a single batched request, with the yes-probability used directly as the relevance score.
oh-my-pi
⌥ Coding agent with the IDE wired in
FastMCP jev_search transform
Two-stage MCP tool search: a wide Choice coarse-ranks the whole catalogue, then a shortlist gets full descriptions plus one Noul each to decide whether it does the job at all.
jcode: memory recall without embeddings
Replaces the whole retrieval stack for memory recall — no embeddings, no BM25, no reranker — with one batched Noul per candidate memory.