2026年9月24日 发布的项目

Thinking coreutils

✨✅ The easiest decisions your code will ever make.

Jev-powered video highlights and cited summaries from subtitles and scripts

Fast browser and macOS computer use for MCP agents. Local execution, TypeSafe Jev decisions, verified outcomes.

A simple demo using jev

Agent skill for designing, building, testing, and tuning bounded JEV decision layers

位于 nginx 与大模型后端之间的前置过滤反向代理：逐请求提取用户输入交给 JEV 判定，有害拦截、正常透明放行

Fast, cheap browser sub-tasks for Claude and other agents: TypeSafe Jev decisions on top of browser-harness

Windows 微信回复助手（非官方修改版）：本地离线 OCR 读屏 + 模型起草候选回复 + 一键填入微信输入框，可选自动发送。不 hook、不注入、不读微信数据库。

SAP Commerce extension using TypeSafe's Jev to moderate product reviews and suggest product categories and classification attribute values: dry runs on your own data first, an audit record per decision. Plus a Claude Code skill.

Jev-powered Playwright test selection

A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.

Jev-like decisions. Strong C++ types.

Hands-on LangChain examples of Jev, TypeSafe AI's decision model: support ticket triage, model routing, reply guardrails, tool selection and finance-inbox fraud checks. An LLM writes; Jev decides.

Small, honest demos of TypeSafe's Jev inside tools data engineers already use

Pass-through model router for Claude Code and Codex CLI that picks a model tier per human turn with Jev, TypeSafe AI's decision model

Hermes plugin for TypeSafe Jev decision routing via OpenRouter + session-start skill pre-loader

OpenJev: An Opencode plugin that replaces text-generation decisions with Jev (TypeSafe System One).

Unofficial Elixir client for the TypeSafe AI API — typed structs, Req-based HTTP with retries, and ergonomic noul/choice/score questions. Not affiliated with TypeSafe AI.

One AI skill + MCP server for Claude Code, Codex and Hermes: Jev (TypeSafe) gates large-model turns (event triage, review verdicts, owner questions, tool choice), runs build-and-repair loops with independent review, routes models and skills, and guards Git steps. Script-only watch mode and a shared HTTP server.

Plain-English browser QA for Claude Code, judged by TypeSafe's Jev on Cloudflare Workers AI

Pi extension that audits rpiv-todo board drift every 10 agent loops using TypeSafe's jev model, injecting corrective nudges when the agent wanders off-task

The first screen-time app built on Kev and Jev. Local-first on Apple silicon for free & privacy. Blocks the mechanism (Shorts, feeds, livestreams), not the site or app.

Unofficial, dependency-free Go client for the TypeSafe AI System One API and the Jev model. Validated responses, masked credentials, bounded retries.

Typed decisions (choice/score/noul) from one encoder pass - faster, better-calibrated successor to Laya, Jev wire compatible

Claude Code plugin + zero-dependency CLI for TypeSafe's Jev: judge items in bulk with calibrated yes/no, pick-one and rubric answers; handle the confident ends in code, review only the uncertain band.

Seven decision models, measured as the candidate list grows, the option order changes, and the wrong answers stop being obvious.

Select which allowlisted CI jobs to run after a change. Jev decides; your workflow stays in control.

Control your Windows PC by voice. Speech-to-text runs locally, and TypeSafe's Jev picks which app, site or action you meant.

jev-crush：把一段双人聊天读成情绪、意图和好感信号。贴进微信记录，标签标在气泡上。Jev 判断，MIT。

One sentence in, a product demo video out. Jev drives your real product in a browser; an index built from your source code guides it.

Jev Research Index is a bilingual catalogue of papers, software projects, interviews, public analyses, demonstrations, and social-media material related to Jev, the TypeSafe AI System One typed probabilistic decision model.

Demo app: Jev (TypeSafe System One) use cases with the AI SDK and shadcn/ui

A Magic 8 Ball that asks Jev instead of picking at random. Convex + AI Gateway + three.js.

PAVE skill for non-autoregressive decision models (Jev / Laya / TypeSafe): typed Choice, Score and Noul answers with calibrated probabilities

Chrome extension that filters X timelines with your own TypeSafe Jev API key, or GLiNER-Decide locally

Extensão gratuita que usa o Jev (TypeSafe) pra marcar no Instagram, X e YouTube o que vale copiar e comentar. Não oficial.

A .NET client for the System One API used by Jev and compatible Laya servers

A decision layer for agent control flow — yes/no, choice and rubric questions answered from one token's probabilities, measured against labelled sets — with a Claude Code permission hook and a trainable local judge

An AI with its hands on the decks: real songs, real DJ moves, every move a tool call decided live by Jev in ~150 ms

Finds out whether Claude Code actually did what you asked, not just what it cost.

Jev System One for Claude Code — typed Choice/Noul/Score via live TypeSafe API (mirror of opencode-openjev, live-only MCP)

OpenJev: An Claude plugin that replaces text-generation decisions with Jev (TypeSafe System One).

Fork of codex-with-chatgpt: TypeSafe Jev + deterministic rules decide when Codex hands work to ChatGPT web (plan, debug, review) and when it switches back. 用 Jev 自动决定 Codex 与网页版 ChatGPT 何时切换。

Reliability testing for probabilistic AI decisions in system-one-models.

本地运行的手绘风格探索工具：借助 TypeSafe Jev 按主题筛选 261 条风格资料，并复制用于图像生成的提示词。 A local hand-drawn style explorer powered by TypeSafe Jev.

Invisible CAPTCHA demo: browser behaviour becomes a plain-English story, and TypeSafe's Jev decides person or bot.

CLI tool to query TypeSafe AI's System One API (Jev model). Designed for scripts, shell pipelines, and agent tool calls where you need fast decisions without invoking a full LLM workflow.

Research notes and an interactive Cloudflare Worker demo for Jev, TypeSafe AI's structured decision model

.NET client for Jev, TypeSafe's System One model. Send state and typed questions, get calibrated structured answers.