Gatekeeper
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
Intent routing (意图路由), Human escalation (人工升级)
choice, 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: gatekeeper/jev.py
Summary · 摘要
Claude Code hook that decides which agent or skill should handle a prompt before the AI picks one: YAML rulebooks settle what code can, Jev answers which handler owns the rest as a Choice, and confidence bands turn that into route, suggest, confirm, escalate, block or allow.written by a model
Claude Code 钩子,在 AI 自行挑选之前决定由哪个智能体或技能处理一条提示:YAML 规则手册先处理代码能判定的部分,其余的由 Jev 以 Choice 回答归哪个处理者,再按置信区间转成转交、建议、确认、上报、拦截或放行。模型撰写机翻
Notes · 备注
Fails open: if Jev is down or slow, nothing is denied. Its starter thresholds are the docs' illustrations, and its 20-of-20 bench uses deliberately clear-cut prompts, as the README says. Prompts go to TypeSafe with secrets masked on a best-effort basis. Row drafted from the discovery queue (issue #14) by an AI assistant that read the README and the cited file on 2026-11-01; a maintainer has not yet read the call site.
故障时放行:Jev 不可用或超时时不拒绝任何请求。README 说明,初始阈值取自官方文档中的示例,20 题全对的测试集用的是刻意清晰的提示。提示会发往 TypeSafe,其中的密钥尽力做了遮盖。本条目由 AI 助手根据发现队列(issue #14)起草,于 2026-11-01 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/gatekeeper.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
TypeSafe AI n8n node
TypeSafe's own n8n community node. Evaluate asks Jev typed questions about each item and adds the answers; Route sends each item to an output by one answer, with a fallback output for low-confidence choices and an uncertain one between two noul thresholds. AI Agents can use it as a tool.
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.
Airflow LLMBranchOperator with Jev
Turns downstream task ids into a choice option set, with a minimum-confidence gate that routes uncertain runs to a human.
Inbox Zero: seven email decisions
Seven distinct email decisions, each with its own separately chosen threshold, falling back to the normal LLM on any error.
jev-chat-jarvis
An Android reply co-pilot that judges intent, timing and risk from on-screen text, while separate models handle OCR and drafting.