2026년 9월 19일 출시

Convai Innovations의 Laya 모델을 ONNX Runtime으로 실행해 Node.js와 TypeScript에서 타입이 지정된 분류와 점수 평가를 제공합니다. Node.js 20 이상에서 @receptron/laya를 설치하고 Laya를 로드한 뒤 상태와 질문을 systemOne에 전달합니다. 사용 후 인스턴스를 닫습니다.

DocJev는 PDF, DOCX, PPTX를 분류하거나 묶음 문서를 범주별 페이지 구간으로 나누고 선택적으로 PDF를 내보냅니다. uv로 Python 패키지를 설치하고 TYPESAFE_API_KEY를 설정한 뒤 분류 규칙으로 docjev classify 또는 split을 실행합니다. Office 형식에는 LibreOffice가 필요합니다.

LLM2Jev는 로컬 언어·시각 모델의 프리필 logits로 후보를 평가하며 토큰별 답변을 생성하지 않습니다. 독립적인 Jev 방식 구현이며 System One 호환 HTTP 엔드포인트를 제공합니다. SGLang, Transformers, MLX를 Python이나 HTTP로 사용하고 지원되는 텍스트·이미지를 입력합니다.

실험적 CLI로 평가, 레이블 작성, 정의 제안을 반복해 이진, 다중 클래스, 다중 레이블, 점수 함수를 개발합니다. Jev는 TypeSafe, Vercel, Cloudflare를 통해 데이터를 평가하며 GEPA의 성찰 모델은 별도 설정합니다.

Jev 방식 Choice, Score, Noul 작업을 위한 공개 모델을 제공하며 Verdict와 Verdict 2.0을 구분합니다. Python HTTP 서버로 webgpu-demo를 제공하고 문서의 브라우저 데모를 엽니다. 모델 산출물과 평가 기록은 별도 링크로 확인합니다.

jeff는 GLiFormer 가중치로 Jev 호환 System One API를 제공해 Choice, Score, Noul을 처리합니다. Python 3.12와 uv로 체크포인트를 받고 JEFF_API_KEYS를 설정해 localhost:8000에 연결합니다.

The System One harness for System One models. Run Jev and other System One models locally or directly on HarnessRouter.ai.

JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる

A small extension that demos the combination of Jev x WebMCP

Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model

lint text in code by jev scorerer

Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples

Open-source AI email triage for Gmail. Sorts your inbox into Needs reply, Updates, Promos, Sales and Spam with Jev, TypeSafe AI's decision model, via Vercel AI Gateway. Read-only, runs locally, 1,000 emails in about a minute for 3 cents.

TypeSafe Jev action selection inside Codex Computer Use

Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.

An open training and inference stack for Jev-style decision models. Train models to score dynamic candidate branches from a shared prefix, with support for high-cardinality choice, calibration, and fast batched inference.

grep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev.

Everything you need to run TypeSafe's Jev with Claude Code: a tool-call guard, tier guard, file search, browser agent, review, belay, compaction and installers.

Supersimple way to serve LLMs as a Jev-like endpoint

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev

Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxonomies, dedupe, PII detection, extraction, search re-ranking and a browser agent.

Jev-powered relevance filtering and reranking for RAG in Python.

用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.

24/7 market-making system around Jev (TypeSafe System One) decisions: deterministic state, calibrated judgments, hard risk vetoes.

📡 全网最全 · The world's most comprehensive tracker of the Jev (TypeSafe AI System One) ecosystem — 220+ documented cases · 108 confidence-graded entries · verified & rescanned every 3 hours · API access guide included

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.

TypeSafe SDK in Swift

Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.

Jev-powered decision layer for DeepSeek Harness

sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev model

Jolt implementation of Laya non-autoregressive System 1 decision engine

JevMail - Self-hosted AI email classifier for Gmail powered by Jev. Create custom labels, organize your inbox, and filter spam with confidence and cost controls.

Rebuild a site's internal link map in seconds with Jev, race Claude Opus 5 on the same queue, and let a deep model rewrite the rubric from the disagreements.

.feels() on anything — the AI if statement as a real, typed method. Jev + BAML.

The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev.

Run SemIf (Jev-style semantic-if decisions) on a CPU — no GPU. Reads typed option probabilities straight from an open model in one forward pass, plus a web UI.

Classify your inbox with Jev (TypeSafe's System One model) — tag, move, flag, and notify, all config-driven.

Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay, over the Chrome DevTools Protocol.

if you're experimenting with jev it will be easier from here

A Swift client for TypeSafe AI's Jev — typed judgements, not text

Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG

Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed classification model — and explains every decision.

One local endpoint. The right model for every turn — enforced in code, not prompts.

Jev for PHP, TypeSafe AI PHP SDK

Fast, bounded browser agents powered by Jev and agent-browser — typed actions, research, classification, and safe orchestration.

Jev + TypeScript SDK demo

Chrome extension that labels every post on X (Substance · Humor · Chit-chat · Promo · Junk · AI-written) with TypeSafe Jev, and hides the ones you don't want.