Skip to content
JevDirectory.org
CommunityCookbooks & Demos62 starsVerified 2026-09-22

Jevmail

A local, read-only Gmail triage app that sorts mail into five trays with Jev: each message becomes one experimental_evaluate call answering tray, urgency, and human-written questions, and 1,000 emails sort in about a minute for around 3 cents.

Open github.comfazlerocks/jevmail
Category
Cookbooks & Demos
Published by
Community
Author
fazlerocks
Added
2026-09-22
Tagscommunitytypescriptprivacyclassificationvercel

Highlights

  • Five trays — Needs reply, Updates, Promos, Sales, and Spam — plus a 1-5 urgency score, with Jev's top two probabilities shown per tray.
  • Requests only the gmail.readonly scope, so it cannot mark read, label, archive, report spam, or send; trays, corrections, and Done live in a local SQLite file.
  • Results are stored with their probabilities, and your corrections are stored separately so Jev's original answer is kept.
  • Needs Node.js 22.18+, pnpm, a Google Cloud OAuth client, and a Vercel AI Gateway key; Jev is free on the Gateway's free tier at 5 calls per 5-minute window.
  • The README notes it is not affiliated with TypeSafe AI, Vercel, or Google, and Google testing-mode refresh tokens expire after 7 days.

Quickstart

bash
git clone https://github.com/fazlerocks/jevmail
cd jevmail
pnpm install
cp .env.example .env.local
pnpm dev

Watch out

MIT-licensed; needs Node.js 22.18+ and pnpm plus Google Cloud OAuth credentials and a Vercel AI Gateway key, and Google testing-mode refresh tokens expire weekly.

More like this

Jev workflow builder
115GitHub stars
A multiplayer demo workflow builder for Jev built with Liveblocks: wire Jev and LLM steps together, call the workflow through a REST API, and preview test runs with shared state and cursors.
Cookbooks & Demos#community#typescript#demo
Communityjev-workflow-builder
Jev Web Analyzer
3GitHub stars
A small demo app that fetches a URL, turns the page into clean Markdown, and asks Jev ten bounded Choice questions about what a first-time visitor is likely to understand.
Cookbooks & Demos#community#typescript#demo
Communityjev-web-analyzer
Soupbase
3GitHub stars
A Chinese and English lateral-thinking puzzle site hosted by Jev: Choice questions classify player questions and check proposed solutions against required facts, while code enforces confidence thresholds before a puzzle is marked solved.
Cookbooks & Demos#community#typescript#games
Communitysoupbase
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A playable 16-judgment demo

AI multiple choice, not essay writing

Screening agent actions with Jev

😎Nick 常胜
😎Nick 常胜
@isNickMa
·

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.

Image
Image
Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read 1 reply

Cua's small System One models

A 706K-parameter form filler

Arsh - 16 y/o builder
Arsh - 16 y/o builder
@be_arsh
·

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

Cua
Cua
@trycua

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

Image
Reply
Read 1 reply

Navigating Neo4j with Jev

思维怪怪
思维怪怪
@0xLogicrw
·

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

Image
思维怪怪
思维怪怪
@0xLogicrw

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

Reply
Read 35 replies