Lançamentos de 18 de setembro de 2026

Um modelo não autorregressivo responde perguntas choice, score e noul; um roteador seleciona o checkpoint. O servidor próprio expõe POST /v1/systemone para clientes Jev existentes, mas executa o modelo Laya.

Hermes Jev Skills oferece habilidades reutilizáveis de seleção de modelos, busca, filtragem de memória, triagem e ações no navegador. Jev faz escolhas delimitadas, como selecionar modelos ou ordenar trechos recuperados; o modelo hospedeiro escreve o texto. Funciona com Hermes, Claude Code e Codex. O modo sombra registra decisões sem trocar o modelo.

Von avalia perguntas independentes em uma passagem para classificação, verificações de sim/não e pontuações ordenadas. É um modelo System One separado, com API compatível com TypeSafe, executado no processo ou via HTTP. Use o SDK Python ou TypeScript, ou disponibilize o modelo local com von serve.

Jev Browser Use cuida de navegação, cliques, alternâncias e rolagem; Codex digita o texto e verifica o resultado. Jev escolhe ações com base no texto de acessibilidade; a conexão Computer Use existente as executa. Exige Node.js 22+, Codex conectado ao navegador e credenciais correspondentes de TypeSafe ou OpenRouter.

O Simple Jev classifica e pontua com modelos compatíveis do Hugging Face, montando respostas JSON a partir dos logits do próximo token sem gerar uma resposta textual. Envie o contexto compartilhado em state ou messages, com perguntas tipadas, para POST /v1/classifier no servidor configurado.

O OpenJev lê respostas tipadas das probabilidades de modelos abertos: escolhas, notas e julgamentos binários, com perguntas sobre imagens no modelo principal. Aponte a URL base do SDK TypeSafe para seu servidor ou o serviço documentado e chame system_one com estado e perguntas.

A biblioteca identifica formulários do IRS e tipos de página a partir do texto extraído e de um cadastro JSON de descrições. Use classifyPage com linhas, jevBackend e criteria.json. As funções PDF exigem Poppler, e o backend precisa de chave TypeSafe.

JevRouter escolhe modelos, agentes, habilidades, ferramentas MCP e CLIs, com decisões únicas ou planos em etapas. Use route, plan, SDK ou configuração de agentes com TypeSafe ou OpenRouter; o provedor demo identificado funciona offline.

O jev-gateway encaminha decisões de ferramentas ao Jev e mantém o restante com o modelo habitual. Instale o pacote npm e abra o agente autenticado pelo lançador jev-, configurando o provedor uma vez.

Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it

grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.

Fish-style zsh history autosuggestions ranked by Jev (TypeSafe)

Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence.

A tool calling chat bot built with Jev and no LLM.

Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

High-throughput synthetic and pretraining dataset sifter for TypeSafe Jev. Rust streaming core, Parquet and JSONL I/O, typed Choice/Score/Noul judgments, speculative fan-out, 24.0 rows/sec measured.

Free Rust SEO and GEO toolkit powered by TypeSafe Jev: 58-rule audits, site crawls, AI citation checks, rank drift, CI gates, 15-tool MCP. Zero cost.

A decision cache for TypeSafe Jev-class models — memoize decisions so repeats are free, deterministic, and shareable. One 2 MB binary.

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.

Ruby client for decision models such as Typesafe Jev

Route HTTP requests by meaning. A semantic router for Hono powered by Jev.

Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post

Classify first. Read selectively. A portable agent plugin and MCP tool for batch text classification.

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

Catch code issues before they catch you.

Replicating Jev with a local LLM

Data extraction for systematic reviews, quoted from the papers. Ask a trial report and its supplements your extraction form or a RoB 2, ROBINS-I, QUADAS-2 or TIDieR template; Jev points at the lines, every answer is a verbatim quote with its page, you check it and export the table. Files stay in your browser.

A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections.

A codebase scanner that helps you not run malicous code

Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.

Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions

A Document OCR Router to help route pages based on content.

Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文為主的雙語 repo。

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy

Open-source macOS AI computer use and native GUI automation on Apple silicon. Jev + OmniParser CoreML + Apple Vision OCR. Bring your own OpenRouter, Vercel AI Gateway, or TypesafeAI token.

Command-line tool for TypeSafe's Jev AI model

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.

2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model

Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter

ALGAL is a programming language and VM for AI agent programs that wait for approval and leave receipts you can replay.

Claude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else

Everyday Stocks Status with Jev

Jev-powered plugins for coding agents

Claude Code plugin: Jev for rule checks, verbatim compaction, and prompt routing

用“Elon的工作”，享无福X！

Real-time drone swarm autonomy simulation using Jev for fast System 1 reflex decisions and collision avoidance, with optional System 2 reasoning for strategic guidance

The first general-purpose System One agent for Jev

Probabilistic control flow for Ruby and Rails - powered by TypeSafe's Jev