Launches on September 20, 2026

Style and quality linter for Norwegian and English text - MCP server for agents, with TypeSafe's Jev as the judgment layer. Reports findings, never authorship verdicts.

AI triage layer for MP CM Helpline 181: Jev typed decisions + Claude, built at Claude Code Build Day Bhopal

Survey respondent quality control with deterministic rules plus semantic judgments from TypeSafe's Jev model — a fully reproducible worked example

Unofficial AXI-style CLI for TypeSafe System One models, including Jev.

Demo de un interceptor de fraude simulado que compara en paralelo un modelo Sistema 1 (Jev, TypeSafe AI) con un LLM (Gemini) sobre transacciones sintéticas: velocidad, costo por llamada y decisiones. Proyecto personal de experimentación, no es un benchmark.

you already test your code. this tests what your agent actually did (powered by jev)

A high-performance content filtering userscript for X (Twitter), combining instant local rules with Jev (TypeSafe System One) semantic decisions to block spam and hidden promotions with sub-100ms latency.

Typed decisions, not chat — shadow decision layer (Jev / TypeSafe AI), with a measured comparison against our live CRM.

An unofficial Dart SDK for the TypeSafe AI API

LLM-as-judge

so you can jev in rust

.NET SDK for TypeSafe AI

Ergonomic, strongly typed Rust client for the TypeSafe System One API (Jev)

A demo of personal finance tracker powered by TypeSafe AI's Jev model

A port of the Typesafe Jev SDK from typescript to Lua

Real-time Super Mario game autonomously controlled by TypeSafe AI's "Jev" System One Decision Architecture. Features sub-100ms decision loops, live prompt & probability telemetry, multi-provider support (OpenRouter Jev & Groq LPUs), and an offline neural simulator.

TypeSafe System One for Pi: a consent-gated judgment tool and workflow design skill

Official Rust SDK for TypeSafe AI (System One / Jev typed decisions).

An unofficial SDK for TypeSafe AI

TypeSafe Go SDK

This is an unofficial community port and is not supported by TypeSafe.

Unofficial async Rust client for the TypeSafe System One API (Jev)

An autonomous Tetris experiment played by JEV through TypeSafe System One.

TypeSafe Jev judge for UEFN Ducky Automations and Pipelines. Not a chat model.

A configurable Chrome extension that filters AI slop, engagement bait, generic filler, and empty hype from social feeds using Jev

A local TypeScript demo comparing Zod upgrades with TypeSafe Jev assessments.

Which lines of your code does that dependency bump actually touch? Evidence-linked upgrade review for JS/TS — points at your line numbers, and says plainly when it has no evidence. Runs locally, no API key.

On-demand CLI that decides where a task should run (Claude Code, Codex CLI, or an isolated Orca worktree) and optionally uses TypeSafe AI's Jev model via OpenRouter to make that call.

vercel ai-gateway 转换为标准TypeSafe-AI接口

Test search over any Obsidian vault with zero labelling: the vault's own links are the answer key. Plain rankers built in, plug in your own, optional Jev reranker.

Việt hoá font pixel/bitmap — kèm bản Departure Mono Viet 134/134 ký tự

基于jev模型的语音释放魔法技能网站

Weekend restaurant picker: Amap POI search + TypeSafe Jev scoring (FastAPI web UI).

Jev look like in a very rudimentary way, great for indie hackers.

Windows UI Automation screen-to-text, MCP server, and Jev-gated computer use

油猴脚本：用 TypeSafe Jev 模型对 X 评论区做语义级垃圾评论过滤（识别形近字/乱码变体，支持隐藏或折叠占位）

X/O vs Jev — tic-tac-toe with TypeSafe Choice

Zynn Explorer: browse any Postgres database and query it in plain English, powered by TypeSafe Jev