Launches on September 23, 2026

Experimental native Codex Desktop and CLI model routing with Jev and a configurable allowlist

Crush 好感监控器的 Windows / macOS 安装包（第三方打包，源码与版权属原作者 FerryCorleone/crush-monitor）

Typed, probabilistic decisions (Choice / Score / Noul) for System One tasks, powered by TypeSafe Jev, with OpenAI and Anthropic as alternative engines

Checks whether a coding agent completion claim is actually true: deterministic evidence gathered in code, one batched Jev assessment, and a pure policy. DSH plugin.

DSH-native context compaction that keeps text verbatim: scores every tool call and result with Jev, drops only the stale ones, and falls back to DSH native summary when unsure.

用 TypeSafe Jev 给 Gmail 自动分类：写回标签、钓鱼检测、退订分析、Chrome 侧边栏面板

A little System 1 for Claude Code: a Go proxy where Claude pre-writes replies to what you will likely say next, Jev checks the match, and a hit lands in about 270 ms with no model call.

Let TypeSafe Jev decide whether a message you send mid-turn should steer, queue, or interrupt your coding agent. Claude Code plugin; Codex CLI in testing.

Voice-controlled 3D smart home demo powered by TypeSafe Jev (Next.js)

Daily research monitor for standing questions: deterministic Python owns the loop, TypeSafe Jev screens sources per question, Qwen writes the notes (pilot)

Benchmark of TypeSafe's Jev as a malicious agent-skill detector on MalSkillBench, with a verify-and-escalate cascade

A brain scan for your Obsidian or markdown vault. Redacts each note on your machine, asks TypeSafe's Jev typed questions about it, and lets plain code decide. Shows the bill first, meters spend against a ceiling, never deletes a note.

Jev voice-controlled computer use: hold a key, speak, and Jev operates your apps. Windows today; macOS, Linux and Android ports welcome.

Find out whether a smaller model could handle some of your AI agent’s routine choices.

Turn a user's search sentence into filters your API already accepts, powered by Jev

⚡ High-speed, zero-hallucination System-1 intelligent tagging assistant for Obsidian powered by TypeSafe Jev

A 184M-parameter decision engine delivering calibrated distributions from one 22ms forward pass while matching models 2.3x its size.

Creating system one model just like jev. with different experimentation

OpenCode 2 plugin that sends every shell command (local or via FarHand) to TypeSafe's Jev and asks you first when it leaves files outside the project, installs software globally, changes global settings, is harmful or exposes private data

Pi coding agent extension that shifts to the right LLM for each prompt, using a local (Laya) or remote (Jev) decision model to judge task difficulty.

Self-hosted gateway for LLMs and decision models. Claude Code, Codex, OpenCode and any OpenAI/Anthropic SDK app reach any provider (OpenRouter, Groq, Ollama…) with context pruning; Jev and open-rlcd System One decisions get audit and calibration. Live dashboard, single Go binary.

这是 Jev 海龟汤 — 一款基于 Jev 模型打造的开源海龟汤情境猜谜游戏。每一道「是 / 否 / 无关」的判断，都由 Jev 现场推理；每一次「还原真相」的内容，都由 Jev 给出判断。没有预设脚本，只有会思考的 Jev，和一款"活"过来的海龟汤。UGC 内容支持，题库因你而丰富。

High-speed dual-process browser agent combining sub-150ms Jev reflex decisions with Stagehand stealth automation and Gemini/Claude System 2 fallback.

A fast System One decision model (Jev or local Laya) picks which LLM answers each prompt: OpenAI-compatible Go gateway + decision benchmark

Deterministic-first cognitive orchestration with bounded TypeSafe JEV supervision, evidence-aware escalation, and privacy-minimizing telemetry.

Exact tmux control with optional read-only Jev judgments for agent panes.

Agent make dozens of silent judgments a turn: is this done, is this correct, do I have enough to decide, which way now. Made inside your own text stream, those judgments are uncalibrated and biased toward finishing, you tend to certify your own work. judge hands one such judgment to Jev.

jev typesafe-ai implementation to enhance pure deterministic decisions and other modeling

AutoBot is a Chrome-compatible browser extension.

Agent skill for writing programs with Laya and laya-cli — local typed decisions (Choice/Score/Noul), port of building-with-jev-skill to Laya

Classification of human/agent messages using Jev in Claude-Code/OpenCode

40-agent, ~10,163-dimension security analysis swarm (static + live ops) with a scored 46-chain exploit planner and Jev (TypeSafe System One) decisioning. Built and verified; source available on request.

Probabilistic pull-request risk triage using Jev and deterministic review policy.

EvidenceLens is an open-source research build for testing what we believe may be JEV's ideal use: bounded semantic evidence review and human-review triage.

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

Serveur MCP pour piloter Firefox avec Claude : Jev (TypeSafe) choisit les clics, Claude planifie. Benchmark inclus.

An MCP server and CLI that rank postings against your profile, explain every score, and measure the ranking against your own judgment.

FormPilot: AI form-filling Chrome extension

Fuses two System-1 decision models (Laya + Jev) into one auditable verdict — confidence-weighted fusion, disagreement escalation to a local adjudicator, append-only JSON decision logs.

Ask a dense data grid in plain language; get a previewed, undoable view change. Headless TypeScript, React, TanStack Table, shadcn. MIT.

Label and prioritise Gmail with a language model. Reads mail through himalaya, classifies each thread with Jev (TypeSafe) over OpenRouter, and applies Gmail labels and colours. Dry run by default, idempotent, no state file.

Local retrieval without embeddings. Every answer comes back as the original passage with its coordinates (path:start-end), so a person or an agent can open the exact lines. No Embedding, Zero Cost, Fully Local.

An experiment: rebuilding a web page's accessibility tree in under a second with TypeSafe's Jev. Evals + a Chrome extension.

Find Amazon keyword ideas with Nexscope and evaluate their relevance to listing text with Jev.

Fish-style zsh autosuggestions ranked by Jev (TypeSafe)

Independent benchmark of TypeSafe Jev (System One) vs cheap and frontier LLMs: accuracy, calibration, latency, cost

CLI client for TypeSafe Jev (System One) structured decisions: noul / choice / score / classify

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

Jev (TypeSafe System One) operating a web page through its DOM — no WebMCP required

Generative painting canvas where Jev, TypeSafe's calibrated decision model, picks paint materials and colour palettes for 105 procedural sketches. FastAPI + React + TypeScript.