Skip to content
CommunityTools & CLIs

jev-suite

Four Java checkers — sponsored video, hiring fit, edit fidelity, and rental listings — that keep thresholds and vetoes in unit-tested code.

Category
Tools & CLIs
Format
—
Published by
Community
Author
klauswg
Added
2026-09-28
Last verified
2026-09-28

klauswg/jev-suite

User repository on GitHub

View on GitHub

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

GitHub stars
33
Forks
0
Primary language
Java
License
mit
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Sep 2026.

Highlights

  • jev-proof, jev-fit, jev-fidelity, and jev-rental each ask one evidence question and leave the final say in Java.
  • A missing model degrades to review. No retrieved evidence fails the check closed.
  • Calibration runners exit 2 without an API key. --allow-mock watermarks the output.
  • The proof app's 60-sample note says 68 of 68 gated judgments correct, 12 designed abstentions, and 0 of 10 injection flips.
  • The rental app lists gated accuracy 0.910 against 0.854 raw on 178 claims.

Quickstart

bash
mvn package

Watch out

MIT. Needs JDK 17+ and Maven. jev-proof also needs yt-dlp. Sample sizes are the README's own calibrations, not an independent replay.

Related terms

Glossary definitions related to this entry.

More like this

A Java gateway that asks Jev four questions about a deposit or withdrawal, then applies a direction-aware routing matrix in code.
Tools & CLIs#community#java#security
20.8kGitHub stars
Browser Use's ultrafast agent: Jev picks an operation and an element from an indexed action space in one request, and a small LLM writes text only when the action is TYPE_TEXT.
Tools & CLIs#community#python#browser
7kGitHub stars
A Claude Code plugin and npm library that replaces transcript summarization with Jev keep-or-drop judgments, deleting stale tool calls and results while kept text stays verbatim.
Tools & CLIs#community#typescript#claude-code

From the guides

Original write-ups that draw on this entry.

Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Tools & CLIs#classification#email#security
Read article
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

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.

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

Reply

Cua's small System One models

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

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

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

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

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

Jason Zhu
Jason Zhu
@GoSailGlobal

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

Reply