Launches on September 21, 2026

Jev-style decision model based on LFM2.5-350M

Prova de Conceito do Jev, modelo da typesafe.ai

A pre-compaction advisor for DeepSeek Harness. Runs before the standard `compaction-basic` backend, using TypeSafe JEV to safely prune low-value tool results from model context. Original session events stay in the append-only log; only the model-visible view is replaced with compact markers or archive pointers to reduce context bloat.

A Jev-like decision engine powered by DiffusionGemma and SGLang. Jev with eyes.

hearim (헤아림) — Jev-compatible multi-backend System One gateway in Go

A Go client for the TypeSafe AI's System One API and its model, Jev.

Community-maintained history of Jev / TypeSafe System One APIs, SDKs, agent guidance, and engineering best practices.

Blazing-Fast Token-Efficient Intrusion Detection System (IDS) based on TypeSafe's Jev.

Translate SRT subtitles with structured LLM output and check every translation with Jev.

用 TypeSafe Jev 实时解读微信消息的桌面浮层 —— 未完成的实验项目，判定准确率不达标，附完整踩坑记录

Curated Jev showcases from X, organized by category with media previews and direct source links.

Jev-powered traffic signal control on CityFlow with structured phase and green-time decisions.

n8n community node for Jev by TypeSafe AI: classify, score and check text with calibrated probabilities. Parallel requests and multi-item batching.

Swift framework to access Jev System One model by TypeSafe.ai

grep for the questions you cannot write as a pattern. Reads every function instead of sampling a few. Powered by Jev, TypeSafe AI's System One model.

Paseo plugin that routes each message to a persona on Codex, Claude, OpenCode, or any other installed provider.

Do you need a hosted decision model, or does a small local model match it? Measure accuracy, latency, calibration and cost on your own task.

面向 OpenAI Codex 的边界模型路由器，由 TypeSafe Jev 决策：只在线程开始、新轮次、压缩和子 agent 派生时选择模型与思考深度，工具循环内绝不切换，因此不会打掉 prompt 缓存。

Open-source AI ad blocker for Chrome. No filter lists: TypeSafe AI's Jev model decides what is an ad. Bring your own key.

Speed and accuracy benchmark: TypeSafe's Jev API vs the local Laya MLX typed-decision model on synthetic tasks

MCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe

JEV Smart Router — a Databricks App that uses TypeSafe JEV to pick which model answers each message, then runs inference on the chosen Databricks Foundation Model API endpoint.

Jev walks a real Pokémon FireRed ROM.

Typed SEO, AEO and GEO judgments powered by Jev, a System One decision model. Code owns the rules, the model owns the meaning.

Text-to-SQL where the model never writes SQL — typed, calibrated decisions (TypeSafe Jev) + code-assembled queries

Exact token counting and request-cost prediction for TypeSafe's Jev (tiktoken-style)

A lightweight collection of developer utilities and scripts designed to streamline Jev development process.

First independent head-to-head benchmark of System One decision models (Laya vs Jev) on byte-identical inputs

Dynamic, confidence-aware Agent Skill routing with TypeSafe Jev and Tink

Self-hosted AI trading intelligence platform - scoring engine, two-model AI analyst (Claude + TypeSafe Jev), risk engine, discipline guardian, backtester, React dashboard

Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.

Compare TypeSafe Jev and LLMs on 60 synthetic candidate-experience reviews: four classification tasks, prompt variants, costs, tokens, and reproducible evidence.

Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. A jev_decide tool for DeepSeek Harness (dsh).

Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compaction

Do what I mean: type what you want in plain words and it runs the right menu item in any Mac app. Powered by Jev (bring your own key).

Jev drives your Ego Lite browser: one typed-choice request per step. Single-file, zero-dependency port of browser-use/jev-ultrafast with multi-model benchmarks and extra guardrails. Unofficial.

tell you everything about jev,TypeSafe AI's System One model for typed decisions.

A TypeSafe-native (Jev) coding agent built on Recursive LLM Context Decomposition (RLCD), with a native macOS client

A multi-account manager and API gateway for TypeSafe / Jev. 一个用于 TypeSafe / Jev 的多账户管理器和 API 网关。交流群：1102910606

弹幕照开，噪音别来。用 JEV 为 B 站评论和弹幕降噪：剧透、反串黑、广告、基本盘一键过滤，想屏蔽什么，再写一句话。Chrome 插件，原页生效，MIT 开源。

Jev-powered model and reasoning-effort router for Codex in DeepSeek Harness

One TypeSafe Jev decision per step over the A11Y tree, executed via ADB. No screenshots and ultra fast!

A System One model (jev) plays Craftax; an LLM sets the goals

Jev Slop Guard — a Chrome extension that scores and stamps AI slop on your X and LinkedIn feeds as you scroll

OpenCode v2 plugin that uses Jev (TypeSafe AI) to dynamically select relevant skills and tools per turn, reducing context window usage.

Pytest plugin for semantic assertions on LLM output using Jev's calibrated probabilities.

Chess against Jev, TypeSafe AI's System One model, through OpenRouter. Built with the pico framework.

About calibrating Jev for code reviews

/whisper: a Claude Code skill that optimizes your prompt before it runs and gets better every time you correct it.

本机运行的中文聊天分析工具：Jev 逐句观察情绪与意图 + DeepSeek 解释，数字全部由程序计算，数据只存在本机