Launches on September 22, 2026

A decision model that cannot write a single note writes songs. Code computes, Jev judges, and every call is replayable.

Spring Boot 4 bookstore API using TypeSafe Jev typed judgments via jev-spring-boot-starter

A fast, local-first gateway for aggregating and routing TypeSafe Jev model endpoints | 一款快速、本地优先的网关，用于聚合与路由 TypeSafe Jev 模型入口

A JEV-gated semantic communication layer for parallel coding agents.

tank arena game driving by Jev

A lightweight, auditable Jev testbench built through Agentic Engineering, with frozen evidence, a preregistered null result, and a bilingual technical blog. 基于 Agentic Engineering 的轻量、可审计 Jev 实验台，包含冻结证据、预注册负结果、双语技术博客与认知负债反思。

Near-free GitHub issue triage powered by TypeSafe AI's Jev - typed, confidence-gated labels that escalate only the uncertain cases.

先回｜消息优先级助手 Windows + Android双端工具 JEV规则引擎 + AI自动判定消息优先级

An AI companion that replies only with facial expressions. Jev (TypeSafe System One) judges your message and picks 1 of 14 moods; blobatar morphs its face. React + Vite + Bun.

JevCore Agent — local coding harness (Jev decisions, Guard hard policy, MCP + CLI)

A tiny 0.6B Jev-like model fine-tuned from Kev for browser use: 32.2% step success on Mind2Web, runs in your browser on WebGPU.

Content-based spam detection and review decisions for Laravel, powered by TypeSafe Jev.

Next-Gen Dual-System Autonomous Operating Engine: Fast Reflexes (Laya <35ms) + Deep Reasoning + 23+ Tools (Browser, OS, Web, Dev, Data)

Laya open-weights decision model behind a TypeSafe/Jev-compatible API, as a Railway template

AI text rewriting and document summarization with Jev checks for missing ideas and automatic repair. Local editor and CLI.

用决策模型 Jev 在 planner 请求前做一次廉价判断（带校准置信度的 Choice 原语），高置信判「本轮无需参与」时抑制这一轮，被抑制的轮次节省90%的token消耗。开箱即用：只需填端点与 key，支持 typesafe / classifier.dev / 任意 OpenAI 兼容网关三种接口风格。

A hypothetical reconstruction of Jev, TypeSafe's closed "System One" decision model, in the spirit of nanoGPT: the smallest working version of what black-box probing suggests. It reads a state and answers typed questions (yes/no, pick one, ordered score) with probabilities instead of generated text.

An independent, reproducible benchmark of TypeSafe's Jev against open, CPU-only alternatives — 10,000 decisions, all raw results published.

OpenCode plugin that routes per-request reasoning effort for agents via Jev (TypeSafe SystemOne) — cheap prompts stay cheap, hard ones get full reasoning

Turn any local LLM into a Jev-style System One decision engine: type-safe answers with raw softmax probabilities. 100% offline, zero API cost.

MCP server exposing TypeSafe's Jev through the public OpenJEV API. Send one shared context and several independent questions; get typed judgments and probabilities back — choice, score, or yes/no — not prose. Built for DeepSeek Harness; runs unchanged in any MCP client.

文献分诊 Chrome 扩展：用 TypeSafe Jev 给 Google Scholar / arXiv / PubMed / X / 小红书 的条目打 关注·普通·跳过，折叠或隐藏不值得读的内容

An open-source AI safety stress-test and intelligence hub for leading models and guardrails, including Jev, ChatGPT, Claude, DeepSeek, Kimi, Gemini, Llama Prompt Guard 2, Grok, GLM, WildGuard, ShieldGemma, Granite Guardian and Shieldstral.

基于 Jev 的 Pi 上下文压缩扩展，在原生压缩前筛选过时的工具调用和结果，保留原生消息结构。npm 包下载量突破 690+

Check agent file changes against your project's written constraints, using TypeSafe AI's Jev decision model

Runtime supervision for autonomous AI agents

Test the most important path in your app. Describe it in plain words. Powered by TypeSafe Jev.

Production reranker benchmark: TypeSafe Jev vs Qwen3-Reranker-0.6B on BEIR SciFact and NFCorpus — nDCG@10, cost/query and p50/p95 latency. Quality is indistinguishable; Jev is ~2x faster, Qwen ~4x cheaper. From the team at denser.ai

Learning infrastructure for typed probabilistic decisions from System One models (Laya, and typed-decision providers you bring yourself).

基于 TypeSafe Jev (System One) 原生云端 API 的客观心智裁决与情感动力学罗盘

An open-source System One decision model — Kahneman's term for the fast, automatic judgment faculty. Calibrated choice/score/noul probabilities in one forward pass on small fine-tuned open models. Local on Apple Silicon (MLX), Jev-compatible API, audited experiment log.

Token-efficient agent memory for Claude Code and Codex, using TypeSafe Jev for typed decisions and a primary LLM for validation.

Local alternative to Jev: typed decisions (choice/score/yes-no) with real probability distributions, from any llama.cpp-supported GGUF model. Easy CLI for humans and AI agents. No generation, no fine-tuning, no compiler.

.Net SDK for the TypeSafe Jev API

A plugin that lets you build reusable **solution signatures** for any classification or scoring problem, then run CSV, Excel, or text file datasets through the [TypeSafe Jev](https://docs.typesafe.ai) API and export structured results to Excel.

🧠 MCP server for TypeSafe's Jev model

MCP server + CLI exposing TypeSafe's Jev judgment model as typed noul/choice/score tools — with a typed escalation contract, an action gate, and TypeSafe/OpenRouter/Vercel/mock backends

Markdown to Sanity documents, with a classifier instead of an LLM. Jev decides, code copies. Experimental.

Control Chrome by voice with a Manifest V3 extension powered by Jev.

What Do is a Zeroshot classifier service for System One style models.

Local-first task router for microservices, polyrepos, monorepos, and coding agents.

Can Jev replace an LLM reranker? A benchmark of TypeSafe's Jev vs Claude Haiku and BGE on natural-language search over all 6,245 YC companies, with a live search demo.

Benchmarking decision models (TypeSafe Jev, Convai Laya) on the 2026 Turkish university entrance exam — 593 questions, full controls, uncontaminated test set

Ace Champion: AI-driven decision engine for Hearthstone Battlegrounds shop-phase plays

Deterministic evaluation harness for LLM agents, with a calibrated judge (Jev) that can act as a CI gate.

A browser agent that books a flight from one sentence. TypeSafe Jev makes every bounded decision; a small text model only writes strings; code does the clicking. 12.88s end to end, 4s of it thinking.

results from iterative benchmark runs

An open-source, AI-powered agentic RAG demo that routes questions to documents, OpenAI docs, or the web.

Fail-closed PreToolUse safety hook for Antigravity shell commands using TypeSafe Jev.

Terminal text-adventure driven entirely by TypeSafe AI's Jev decision model - typed choice/score/noul answers, not generated prose