Skip to content
JevDirectory.org
CommunityTools & Integrations3 starsVerified 2026-09-22

jevkit

A Rust CLI that sends terse YAML or JSON question sets to Jev, validates them offline with 13 lint rules before any billed call, and prints parsed answers as JSON.

Category
Tools & Integrations
Published by
Community
Author
ariel-frischer
Added
2026-09-22
Tagscommunityrustcliclassificationskills

Highlights

  • jev ask sends noul, choice, and score questions by file, stdin, or --question-set, and prints parsed answers as JSON on stdout.
  • jev lint runs 13 offline rules in about 0.5 ms and exits 2 on rejected questions, catching asks the API would bill for.
  • Terse question sets are 198 characters versus 308 raw, a 36% writing saving, while the wire payload and API cost stay identical.
  • Ten questions in one request measured 230 ms versus 266 ms for one, for 39% more cost; the API answers questions in parallel.
  • Prebuilt binaries cover Linux and macOS on x86_64 and aarch64, and the installer verifies SHA-256; Windows needs WSL.

Quickstart

bash
curl -fsSL https://raw.githubusercontent.com/ariel-frischer/jevkit/main/install.sh | sh
jev ask -q severity.yaml "The deploy script drops the production database with no confirmation."

Watch out

MIT-licensed. Needs a TypeSafe or OpenRouter key stored in the OS keyring rather than argv; binaries cover Linux and macOS only and Windows requires WSL.

More like this

83GitHub stars
A Rust CLI that ranks agent skills for the next step with a two-stage Jev pass plus lexical prefiltering, with Claude Code hooks, a TUI, abstention, and --why-not explanations.
Tools & Integrations#community#rust#cli
Communityskillranker
35GitHub stars
A Rust CLI that classifies Git commit diffs and messages with Jev into bug fixes, security fixes with CWEs, and change types, then writes HTML or CSV reports from saved scans.
Tools & Integrations#community#rust#cli
Communitycommit-miner
23GitHub stars
A Rust CLI and PyO3 library that streams JSONL and Parquet rows through Jev Noul and Score rubrics, writing clean and rejected records to disk without rewriting content.
Tools & Integrations#community#rust#cli
Communityjev-curate
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

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

Six uses that stuck after 60 days

Security decisions that fit Jev

This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more

TypeSafe AI
TypeSafe AI
@typesafeai

we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)

Reply

A million judged questions