Launches on September 19, 2026

The package runs Convai Innovations’ Laya model through ONNX Runtime for typed classification and scoring in Node.js and TypeScript. Install @receptron/laya on Node.js 20 or newer, load Laya, then pass state and typed questions to systemOne; close the instance afterward.

DocJev classifies PDF, DOCX and PPTX documents or splits packets into categorized page ranges, with optional PDF exports. Install the Python package with uv, export TYPESAFE_API_KEY, and run docjev classify or split with category rules. Office formats require LibreOffice.

LLM2Jev scores candidates from local language and vision models using prefill logits without token-by-token generation. It provides an independent Jev-style implementation with a compatible System One HTTP endpoint. Use Python or HTTP with SGLang, Transformers or MLX, including supported text-and-image inputs.

This experimental CLI develops binary, multiclass, multilabel and scoring functions through repeated evaluation, labeling and definition proposals. Jev evaluates the data through TypeSafe, Vercel or Cloudflare; GEPA uses a separately configured reflection model.

The repository offers open decision models for Jev-style Choice, Score and Noul workflows, including separate Verdict and Verdict 2.0 models. Serve webgpu-demo with Python’s HTTP server and open the documented browser playground; model artifacts and evaluation receipts are linked separately.

jeff serves a Jev-compatible System One API using GLiFormer weights for Choice, Score and Noul decisions. Use Python 3.12 and uv, download the checkpoint, set JEFF_API_KEYS and point the client at localhost:8000.

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.