11 projects · updated 2 November 2026

Other things built with decision models

Projects that do not fit the larger clusters, including data tooling, recruiting and one-off experiments.

11 of these 11 call the hosted API rather than running open weights.

contextgem2.0k ★shcherbak-aiExtract structured data and insights from documents using LLMs and decision modelsPython · Apache-2.0 · pushed 2026-10-28shapeshift1.1k ★anishfnAn input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, works offline.TypeScript · MIT · pushed 2026-09-23crush-monitor334 ★FerryCorleoneCrush 好感监控器:用 Jev 分析微信聊天的情绪、意图和回复表现。本机部署,使用自己的 API Key。TypeScript · MIT · pushed 2026-10-17jev-align313 ★sutro-shBuild calibrated AI Functions from human feedback using Jev and GEPA.Python · Apache-2.0 · pushed 2026-10-28killmyidea273 ★monteduroDescribe your startup idea. Jev decides: kill it, fix it or ship it.TypeScript · pushed 2026-10-17jev-leftpad85 ★fLeft-pad strings with TypeSafe AI's Jev. For reasons.JavaScript · MIT · pushed 2026-10-25HA-Jev82 ★AboveColinAsk your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automations, and a conversation agent for Assist.Python · MIT · pushed 2026-10-26jev-explained36 ★davila7Jev ExplainedTypeScript · MIT · pushed 2026-09-20Jev-Register-Tool35 ★2951461586TypeSafe(Jev / System One)申请 → 确认邮件 → 获批 → 注册 → 建 API Key 全链路工具,纯 HTTP 无浏览器Python · pushed 2026-09-22jev-cookbook16 ★paramjeetnThe complete cookbook for Jev by TypeSafe AI — 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory for the world's first System One AI model.Python · MIT · pushed 2026-09-22typesafe-playground15 ★kavehmzInteractive experiments with TypeSafe Jev, from support routing to 3D driving simulations with real AI decisions and visible sensor inputs.JavaScript · pushed 2026-09-29

Find out what your data actually supports

We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.