No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by yzfly · Agent Tool · ★ 60
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is awesome-jev-zh safe to install? View the security audit →
Awesome Jev ZH Jev 不生成文本。 第一次看到这句话时我以为是个缺陷，后来才发现这正是它的设计核心。 它的用法是：给它一段 state（一封邮件、一行日志、一个工单），再给它几个带类型的问题，它在 70–500ms 内一次性答完——从你给的选项里选一个、在你给的量表上打一个分、或者给出一个 0 到 1 的概率，每个答案都附带一个置信度。输入 $0.042 / MTok，输出不计费。 它的边界也很清楚：要写文案、要总结文章、要解释判断理由，LLM 仍然是更合适的工具。这一条后面还会出现好几次。 那它解决了什么？整理这份列表的过程中，我越来越确信一件事：我们今天写的很多 LLM 调用，本质上只是在做选择题。 拼 prompt、逐 token 生成、剥掉 markdown 代码块、、校验 schema、失败了再重试——绕这么大一圈，只为了拿回 这一个词。这段代码我自己写过不止一次。Jev 想省掉的就是这一圈。 另外有两个数字想先摆出来，免得看完才发现：「快 193 倍」来自 TypeSafe 自己的评测，官方也标注了那是收益上限；而独立评测里，在钓鱼邮件这个具体任务上，直接问它一句只有 62.6% 的准确率，两行正则规则能到 91.8%。完整数据在 冷静看待 一节。 这是 Jev 生态的中文精选列表，外加两份中文指南和一份 图解说明。 非官方整理，与 TypeSafe AI 无隶属关系 · Jev 于 2026-09-15 开放 early access · 所有厂商自评数据都标注了出处 目录 入门 — 官方资源 · Jev 是什么 · 上手 · 规格与定价 · 该用与不该用 · 中文指南 项目 — 热门自动榜 · SDK · 应用 · Demo · Agent 工具 · 复现与评测 资料 — Cookbook 与模式 · 文章 · 社区 · 冷静看待 📘 官方资源 官方文档写得相当清楚。真要弄懂这个模型
| Stars | 60 |
| Forks | 16 |
| Language | HTML |
| Category | Agent Tool |
| License | CC0-1.0 |
| Quality Score | 60.3745562352313/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-23 |
| Created | 2026-09-18 |
| Est. Tokens | ~28k |
Looking for a awesome-jev-zh alternative? If you're comparing awesome-jev-zh with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast
A community directory of projects built on Jev, TypeSafe AI's System One model.
🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.
Typed decisions with TypeSafe's Jev, the first System One model
Curated Jev resources and runnable examples for typed AI decisions.
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisio
Explore other popular agent tool tools:
awesome-jev-zh is Jev / TypeSafe System One 中文精选列表：官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测，附中文上手指南，每日自动收录 GitHub 热门项目。. It is categorized as a Agent Tool with 60 GitHub stars.
awesome-jev-zh is primarily written in HTML. It covers topics such as ai-agent, awesome, awesome-list.
You can find installation instructions and usage details in the awesome-jev-zh GitHub repository at github.com/yzfly/awesome-jev-zh. The project has 60 stars and 16 forks, indicating an active community.
awesome-jev-zh is released under the CC0-1.0 license, making it free to use and modify according to the license terms.
The top alternatives to awesome-jev-zh on Agent Skills Hub include awesome-jev, awesome-jev, awesome-jev. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: