Lançamentos de 22 de setembro de 2026

Shapeshift transforma texto em eventos, listas, temporizadores, divisão de contas e outras interfaces específicas. Jev opcional classifica intenção e sinais; o código calcula datas e valores. A classificação offline por palavras-chave é padrão. Digite no app Bun, escolha e salve o cartão; uma chave TypeSafe no servidor ativa Jev.

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

《Jev 工程学：为 coding agent 而作》完整中文翻译 — 保留原结构与 7 张插图

JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.

AI-driven intraday trading bot for Indian stocks. Jev ranks the Nifty 50 every 15s; code sizes each trade and places the stop; orders go live through Zerodha Kite or Kotak Neo. Day replay, kill switch, daily loss halt, terminal dashboard.

Automatic project memory for Claude Code. Also works with Cursor and Codex.

Provider-neutral System One runtime for TypeScript and Pi

微信（FkWeChat 插件）：长按消息分析意图 / 情绪 / 回复姿态，只在本机弹提示，对方无感知

JevGym is an open-source platform designed to benchmark and facilitate better probabilistic estimation in Jev-alike models

Blazing fast structured decisions for System One open-models self-hosted with a TypeSafe AI compatible API, written in Rust.

Real-time risk triage gateway for exchange deposits and withdrawals — Jev (TypeSafe System One) handles triage only; adjudication stays in deterministic code.

Permutation Invariant Jev

Four decision-quality tools on Jev (TypeSafe System One): Jev answers structured questions, deterministic code keeps the final say.

A tiny jev-like model that answers Choice, Score and Noul questions in one forward pass and returns calibrated probabilities. MLX or PyTorch, fully offline, System One compatible.

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件

Jev decision layer for Muse: a fast, cheap TypeSafe AI gate before expensive agent work — confidence policy, recipes, reference router, honest measurement.

Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint

Two Minds, One Trip. https://jev-trip.vercel.app/

Windows 微信对话分析助手：本地读取、脱敏、TypeSafe Jev 判断与加密历史

Calibration-aware reinforcement learning for adaptive decision systems

Open-source System One decision engine. Typed choice / score / noul with calibrated probabilities. Self-host with Ollama or any OpenAI-compatible model. Apache-2.0.

LLM plugin for accessing Jev and other TypeSafe AI models

Use LLM judgment in regular Elixir control flow.

安卓无障碍版微信判读：只读屏、只弹 3 条 Toast（意图 / 情绪 / 着急 / 建议），不生成回复文案、不发送 · 零第三方依赖，APK 861 KB

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

Jev? Déjà vu. Browser agents that run on instinct, no Jev needed. One look at the page, one call to any open model, one action. Faster than the Jev demo on Google Flights.

200+ plug-and-play Jev recipes: small, calibrated AI decisions that route, grade, gate, compare, and label text for agents, RAG, support, code review, and music. Import from JavaScript or TypeScript, or call the CLI with JSON from any language.

打っている言葉が日本語か英語かをJevに聞いて、Macの入力モードを切り替える道具。個人利用のみ。

Jev for Computer Use

Natural-language constraints for JEPA world-model planning, judged by a decision model instead of an LLM.

Evidence-first long-term experiment memory skill for AI coding agents, with optional Jev decision-model layers

DeepSeek Harness plugin for TypeSafe Jev: typed decisions, configurable guardrails, and Web UI result cards.

PowerShell decisions with TypeSafe AI's Jev model: https://typesafe.ai/blog/introducing-system-one-models-and-jev

DeepSeek + TypeSafe JEV 微信回复助手：Windows 正式版、Apple Silicon macOS 预览版；本地 OCR 与人工可控回复

Benchmark TypeSafe JEV against LLMs, fine-tuned BERT, Laya and zero-shot NLI on text classification: accuracy, calibration, latency, throughput, cost

TypeSafe Jev baseline for DimABSA (SemEval-2026 Task 3) subtask 1: zero-shot and 3-shot valence-arousal regression

Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your docs into each prompt, and check the final answer against the turn's own evidence.

Use Jev everywhere to make & track decisions

DeepSeek Harness (DSH) 推理等级自动选择插件：由 Jev System One 模型判断每条消息值多少思考量，按模型声明的等级自动推导档位，上下文信封让「继续」这类追问继承话题深度，低置信度向上取，任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.

Jev-driven native GPUI testing: Rust accessibility bridge, bounded goal runners, and one-call pi integration.

A hundred hands through Git history — reproducible commit analytics powered by Jev.

JEV-powered market decision bot for stocks, crypto and memes. State in, BUY/SELL/HOLD/AVOID out, paper by default

Self-hosted Jev decision workbench and Feishu bot: automatic choices, probabilities, and experimental word/character writing.

The complete cookbook for Jev by TypeSafe AI — 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory for the world's first System One AI model.

Jev 决策模型驱动的 UI 自动化测试框架：不生成「下一步做什么」的文字，而是在候选元素里直接打分；一句话写用例，pytest 执行，Allure 出报告，每个操作决策中位 458 ms（UI test automation driven by the Jev decision model — scored decisions, not generated prose; ~458 ms per decision）

Local System-One decision models: typed questions in, calibrated probabilities out. General decisions and browser-agent steps.

15 open-source outbound recipes on TypeSafe Jev. Score your LinkedIn network or any lead list against your ICP, catch job changes, triage replies. Local, zero dependencies. 16,711 connections scored for $0.73.

Slams a BAIT, CORP or BRAG stamp onto LinkedIn engagement-bait, judged live by Jev (TypeSafe System One).

AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions kept in code. Accessibility-tree targeting, window-scoped input, clipboard-safe paste, read-back verification. Ships a pip CLI, a pi package and a DeepSeek Harness plugin.