WTF is Jev by @typesafeai? Here’s the tl;dr ELI5: Think AI multiple choice, not AI essay writing. It doesn’t chat. It makes decisions your software can act on: “Spam or not?” “Which tool should this agent use?” “Does this need a human?” The exciting part: roughly 200x faster Show more
Jev Desktop for Codex
A Codex Computer Use plugin that adds bounded Jev decision loops: Codex scopes the task and defines allowed actions, Jev picks an operation and compatible target in one request, and Computer Use performs the click, fill, scroll, or shortcut.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- yikangy873-gif
- Added
- 2026-09-22
Tagscommunityjavascriptcodexcomputer-useagents
Highlights
- All heads are predicted in one TypeSafe request, and only the target head selected by the operation is validated and allowed to execute.
- Reuses the existing Computer Use runtime without a second browser controller, private APIs, Browser Harness, or OpenRouter for field text.
- Consequential controls such as send, publish, payment, deletion, upload, login, and installation return to Codex instead of running in Jev's loop.
- The loopback bridge listens on a random 127.0.0.1 port, pins the TypeSafe endpoint, rejects browser origins, and never retries mutation decisions.
- Version 0.2.0 expands automated coverage to 123 tests and sends an indexed element table instead of a flat action list.
Quickstart
bash
codex plugin marketplace add yikangy873-gif/jev-desktop
codex plugin add jev-desktop@yikangy873-pluginsWatch out
MIT-licensed; needs Codex with plugin support, Node.js 22+, Python 3.10+, and a TypeSafe API key, and the README does not yet prove an end-to-end speedup because Computer Use observation dominates latency.
More like this
571GitHub stars
An experimental Codex skill and JavaScript runtime that has Jev pick macOS Accessibility elements and actions from text candidates, while local policy gates hold sensitive operations for human confirmation.
Tools & Integrations#community#javascript#codex
CommunityJev-cu
94GitHub stars
A structured decision plugin for agent harnesses: Jev recommends among currently available and permitted tools, skills, and agents, and evaluates output quality, returning choices, probabilities, and confidence while the host agent keeps planning and execution.
Tools & Integrations#community#javascript#agents
Communityjev-dsh-decision
22GitHub stars
A security hook for coding agents that asks Jev three typed questions before every tool call and scans tool results for prompt injection, with adapters for Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, pi, OpenCode and ACP.
Tools & Integrations#community#javascript#agents
Communityjev-guard
From the community
Posts from builders shipping with Jev right now.
AI multiple choice, not essay writing
Screening agent actions with Jev
Tested TypeSafe’s Jev (no-text, probability-only model) as an AI agent safety monitor. Checking each action first worked well caught most attacks with almost no false blocks, and much faster than Gemini.
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Cua's small System One models
1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua
A 706K-parameter form filler
cua open sourced a 706k param model that fills a whole form in one 50ms pass the llm agent doing the same form took 23 turns and 39.6 seconds the specialists are going to eat the generalists from the bottom
1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua
Navigating Neo4j with Jev
Jev 这个 waitlist 还是很给力的，昨天申请，今天就能用上。 给已经拿到 API、但还不知道怎么玩的人整理了一份 Awesome Jev，目前我能确认到的 Jev 项目基本都在这里： 1. jev-ultrafast Browser Use 做的高速浏览器 Agent。Jev Show more
前 OpenAI 研究员 Diogo Almeida 创办的 TypeSafe AI 推出新模型 Jev。它有点像一个能读懂自然语言的超级分类器，不生成文本，只返回选项、分数和概率，专门给软件做判断。 普通大模型需要一个 token 一个 token 往外生成，Jev 则可以并行给出多个结果。TypeSafe 还用新的 RLCD
Reranking 33,047 catalog entries
拿 Jev 做搜索重排，我先泼一盆冷水：单独用，它没打赢向量检索 TypeSafe 的 Jev 这阵子很火，一堆项目拿它做重排。我们在 Agent Skills Hub 的 33,047 条目录上认真测了一次，164 条中英文真实查询，9,831 对分级标注，整套只花了 2.6 美元 三个结论 01｜单独重排，约等于没赢 Jev 重排 bge-m3 Show more
有美团、阿里的老哥嘛？ 试试加一路召回、重排（离线、近实时实现），我觉得有奇效 他在文本理解上 跟之前机器学习、llm很不一样 还能自动打标签做特征