npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

jev-use

v0.7.1

Published

Claude Code / Codex / pi plugin that hands the agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.

Readme

jev-use

English | 简体中文

Claude Code / Codex / piJev 的最佳协作方式:把不需要输出内容的任务交给 Jev——加速任务、减少 token 消耗,更快更好地完成任务。

它让 LLM 与 Jev 真正协作:需要输出内容时,LLM 接管;不需要内容、只要快速执行时,交给 Jev。

演示——真实运行,1× 速度

每个演示都是可复跑的脚本,在 bench/examples/;全部数字、方法、方差与告示:bench/RESULTS.md · 第三方实测:docs/evidence.md

安装

npx -y jev-use install    # 自动配置 Claude Code / Codex / pi——检测到哪个装哪个

在 agent 运行的环境里配一个 key(JEV_BACKEND=mock 可无 key 干跑):

| 供应商 | 环境变量 | | --- | --- | | TypeSafe 直连 | TYPESAFE_API_KEY | | OpenRouter | OPENROUTER_API_KEY | | Vercel AI Gateway | AI_GATEWAY_API_KEY |

npx -y jev-use doctor 检查链路。被判断的状态会发往你配置的供应商;JEV_BACKEND=mock 全程本地。插件形态(含路由技能和 PreToolUse 把关):harness/claude-code · harness/codex

作为库使用

npm i jev-use——判断路径零运行时依赖:

import { Jev, check, pick, rate } from "jev-use";

const jev = new Jev();

const { answers } = await jev.judge(state, {
  next: pick("Next action?", { merge: "all green", rerun: "looks flaky", hold: "needs attention" }),
  risk: rate("How risky?", ["routine", "worth a look", "incident"]),
  passed: check("Did the run fully succeed?"),
});
// answers.next → { answer: "merge", confidence: 0.93, confidenceFrom: "reported", escalate: false }

Jev 拍不了板的判决会带着 escalate: true 和类型化原因交还。工具、判决结构、升级契约、CLI:docs/reference.md

小到能读完

| 文件 | 职责 | | --- | --- | | src/protocol.ts | 问题(check/pick/rate)、判决、升级原因的类型 | | src/dispatch.ts | 调用前分路:哪些步骤根本不进 Jev | | src/judge.ts | 筛查 → 后端 → 交还不确定的;gate | | src/jev.ts | 引擎之上的 Jev 客户端 | | src/backends/ | TypeSafe、OpenRouter、Vercel、mock 适配器 | | src/server.ts | 两个 MCP 工具 | | src/cli.ts | installservehook gatedoctor | | skills/jev-use/SKILL.md | agent 遵循的路由规则 |

开发

$ npm run typecheck && npm test    # 单元测试,含各供应商线上格式 fixture
$ npm run smoke                    # 真实 MCP 客户端 ↔ 构建产物 CLI,走 stdio
$ node bench/run.mjs               # 微基准,用你的 key 和网络

主体由 Claude Code(AI 辅助)编写。

MIT © shitianfang