Jev ecosystem projects — page 76

Security & calibration middleware for System 1 AI models like jev & laya

Decision Lab: visual System One playground for building decisions, comparing Jev, OpenJEV, Laya, and exploring what-if changes.

project

Doc, Scott's sidekick: Jev (TypeSafe) wired into Claude Code — checks comments before they're published, keeps effort estimates out of replies, points each turn at the right skill, and routes easy work to a cheaper model.

Bot and pitch detection for risky forms with one typed question to Jev. Zero dependencies, mock mode without a key, recorded live run included.

A JEV-powered decision layer for MCP-compatible AI Agents.

System One foundation and Cordis plugin for DeepSeek Harness | DeepSeek Harness 的 System One 基础能力与 Cordis 插件

A local Jev-compatible decision engine powered by a 1.16 GB quantized 8B model.

repository with configuration via docker-compose to run instance of jev's model such as laya or open-jev

Jev-scored EIP testing-complexity assessments against the ethspecs/pm checklist

A Jev decision layer for Customer Success — 22 typed decisions per inbound message, 14 per account, 10 per outbound draft. Zero dependencies, 38 tests, runs offline.

AI-assisted file organizer built on Electron + Vue 3 + TypeSafe (Jev) - AI 归档建议与逐层查找

A fast iOS simulator agent with a dynamic, indexed action space. Powered by TypeSafe Jev & Facebook idb.

General Viral Gene Annotator, using two tiered AI-architecture

五子棋 vs TypeSafe Jev：本地引擎 + Jev 裁决，附残局与自对弈实验

Jev recognizes glycogen storage disease patterns in synthetic USMLE-style vignettes: one Choice question, full option distributions, 14 preserved runs.

Gate Hermes Agent tool calls with TypeSafe Jev (System One) over OpenRouter — observe, escalate to the native approval gate, or block.

Hacker News scoring Chrome extension powered by Jev