Launches on September 22, 2026

Chrome extension that detects low substance AI slop patterns in LinkedIn posts using the TypeSafe JEV API

Jev is actually not a traditional LLM, it doesn’t generate text. It’s what the TypeSafe AI team calls a System One model: 📖 System One models are a class of AI models built to make fast, structured decisions that software can use directly. A System One model evaluates a state and returns typed answers and probabilities.

Reproducing the Jev decision interface

Ask TypeSafe's Jev a plain-English question, get a calibrated typed answer. CLI + local UI + public Cloudflare Worker + Claude Code skill.

astrbot-plugin-jev

Library for System One usage using Jev for Cyber threat intel

Monochrome 1v1 battle arena for anime, comics, and shows — judged by Jev (TypeSafe AI System One).

AI Engineering knowledge base & Obsidian automated extractor (TypeSafe Jev + DeepSeek)

Agent Skill + estudo verbatim sobre a Jev (TypeSafe AI System One Model): choice/score/noul, RLCD, patterns, SDKs.

Decisioni tipizzate da un modello linguistico, sul tuo computer, senza generare un token. La versione libera dell'idea di Jev.

Autonomous BloxSmith block for TypeSafe Jev: typed judgments and probabilities from text or JSON.

Jev Prune for Claude Code: lossless context pruning, compaction and filtering

use jev, typesafe's system one classifier, to cut claude code costs, and measure which decisions it can take without costing correctness

Claude Code plugin that auto-picks the right model for each turn — micro, low, medium, or high tier — using Jev routing.

Codex plugin that restores Jev-selected tool evidence after context compaction

Codex × JEV 開源工作流：讓 Codex 按需使用 JEV，協助語意分類、候選篩選與修改範圍檢查，支援跨專案規則、請求預算、資料檢查、失敗退回、Mock 測試與用量追蹤。 Open-source Codex × JEV router for on-demand classification, candidate filtering and change-scope checks, with reusable rules, call budgets, data checks, fallbacks, mock tests and usage tracking.

Buy/Hold/Sell outlook for new Magic: The Gathering cards, driven by Commander demand. Price history + EDHREC + TypeSafe Jev judgments.

Preserve exact task evidence across Codex context compaction with optional TypeSafe Jev scoring.

CLIProxyAPI TypeSafe System One (Jev) native provider plugin

system one model serving engine

Chrome extension that hides engagement bait, AI slop, recycled news and posts from countries you pick on X and LinkedIn. Powered by Jev via OpenRouter.

Score web pages for ads, slop, SEO and second-hand content. An agent skill built on TypeSafe Jev: four probabilities per page, no verdict, the caller sets the thresholds.

Chrome/Firefox extension that grades every LinkedIn feed post as a golden nugget, useful, or slop with TypeSafe's jev model

Chrome extension: sort tabs into groups with TypeSafe Jev

Jev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev-advisor builds a structured Jev request and floats the recommendation, probability spread and confidence beside the options - one click to adopt. API key lives in Settings. No prompt changes.

TypeSafe Jev SystemOne structured-judgment plugin for DeepSeek Harness (jev_judge: noul/choice/score)

Jev decision toolkit for DeepSeek Harness: 22 named typed judgments (privacy scan, change-scope, memory triage, batch triage) on one hardened, budgeted, ledger-backed transport. Advisory only.

Jev quality bench for DeepSeek Harness: shadow-accounted dangerous-command judging, injection screening, canary A/B drills, optional gate mode.

Ask TypeSafe (Jev) for structured decisions from inside DeepSeek Harness: typed questions in, calibrated probabilities out.

Jev by deepseek41

Type a description, watch matching emoji fly out of the pile. Built with TypeSafe AI's Jev via Vercel AI Gateway.

Typed Jev decisions, 22 executable recipes, and integration guides for automation harnesses. TypeScript, zero runtime dependencies, MIT.

Evidence-aware semiconductor alert triage research demo with TypeSafe Jev, policy guards, and reproducible evaluation

opencode V2 adapter for fast-jev-compaction: prunes stale tool calls and results from the outgoing request using a typed-decision endpoint

Flappy Bird where you race Jev, TypeSafe's System One decision model, flying its own bird in real time. Built with Next.js and Neon Postgres.

A simulated fruit fly brain and TypeSafe AI's Jev play Pong against each other

JEV evaluation (FM-JEV-01): replay-only, advisory-only evaluation of Foreman-style supervision with TypeSafe Jev. Measures how much safety comes from the model versus a deterministic evidence gate. No worker authority.

PR staging for thruwire/foreman contributions

A Jev-powered policy gateway that checks an AI agent's proposed actions before executing them.

给 Gemini CLI 装上 TypeSafe Jev 做的「质量门」：在关键节点问 Jev 几个结构化问题（要不要返工、这步危险吗、这个请求该不该做），再据此放行、打回、拦截或先弹出确认。

This repository contains a GitHub issue classifier built on Jev, TypeSafe AI's System One model. It labels every new issue with typed values and calibrated confidence in milliseconds, labelling what it is sure about and escalating what it is not. Three guardrail layers guard every write, and a frozen eval suite gates each deploy.

Sorts Gmail into labels using typed judgments from TypeSafe Jev. No dependencies, dry-run by default, never deletes.

Go client for the Jev judgement API - ask structured questions about a piece of text and get typed answers back

A Go library for Jev System One.

TypeScript guideme SDK: a TypeSafe Jev judgment as control flow

Home Assistant integration: TypeSafe Jev decides what each room needs; deterministic code acts, with phone confirmation for risky devices.

Cache-safe adaptive reasoning effort for Hermes, selected by TypeSafe Jev through OpenRouter

Calibrated, sub-second decisions in Claude Code's hooks, answered by TypeSafe's Jev

A pre-registered test of which parts of TypeSafe's advice for its Jev model change the answer.

A2A multi-agent investment research showcase: jev (sequential), jev-parallel (concurrent), and a single-prompt LLM baseline, with a React UI.