jev-user-jury

TypeSafe Jev（System One 决策模型）零依赖网页体验台：浏览器操作 / 意图识别 / Agent 上下文裁剪三大预设场景，发送状态与类型化问题，拿到带校准概率的结构化答案

Match user goals to MCP catalog (two-stage) via TypeSafe Jev

JEV AI Model Demo with FSD

USER + JEV: P(DOOM) PROTOCOL — co-op platform shooter where TypeSafe Jev plays alongside you

A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.

Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.

An OpenAI-compatible proxy that sits between your LLM and your users. It evaluates each sliding window of tokens while the response is still streaming and cuts the stream before a violating token can reach the screen.

Independent, source-linked research on TypeSafe AI's Jev (System One), with 947 rubric-scored public repositories, recurring patterns, datasets, and bilingual documentation.

MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools