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
every
A semantic code search CLI that asks one yes/no Jev question per function and ranks the returned probabilities, screening a whole codebase for a pattern in seconds for cents.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- sufianetaouil
- Added
- 2026-09-22
Tagscommunitypythonclisearchclassification
Highlights
- Each function goes into its own Jev question rather than a shared list, at about 110 questions per request and 4 requests in flight.
- Roughly $0.00001 per function at about 300 input tokens each; 1,302 gin functions ran in 3.7 s for $0.018.
- tree-sitter splits repos into functions for Python, JavaScript, TypeScript, Go, Java, Rust, C#, Ruby, and PHP; other files become 150-line chunks.
- Scores within 0.10 of the threshold are asked again and averaged, and results cache in .every/cache.json as sha256 hashes, never source.
- The bundled selftest reports recall 10/10 and AUROC 1.000 on 20 hand-written functions, which the README calls not a benchmark.
Quickstart
bash
pip install every-cli
export TYPESAFE_API_KEY=YOUR_API_KEY
every --selftest
every "catches an exception and then ignores it" ./my-api --above 0.75Watch out
MIT-licensed. Needs a Jev API key, and the source of every scanned function is sent to api.typesafe.ai; whole-program data flow is out of scope and results are marked coverage: partial.
More like this
18GitHub stars
A grep-style CLI where the pattern is a plain-English description: each line becomes one Jev Noul question, judged concurrently with matches printed in input order, working on tail -f as well as files.
Tools & Integrations#community#python#cli
Communityjgrep
273GitHub stars
An experimental Sutro CLI that evaluates CSV, Parquet, and JSONL data with Jev, asks you to label ambiguous and random audit rows, and uses GEPA to propose improved function definitions.
Tools & Integrations#community#python#cli
Communityjev-align
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
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