typesafe's jev is fun! live demo you can play with: typesafe-demo.val.run
jevgrep
A streaming grep-by-meaning CLI that judges each line with one Jev yes/no question and prints the lines above a threshold, built to sit behind tail -f, kubectl logs -f, or journalctl -f.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- allebee
- Added
- 2026-09-22
Tagscommunitypythonclisearchopenrouterlogs
Highlights
- A match shows up about 0.7 s after the line is written, and it keeps grep's exit codes (0, 1, 2) and pipes cleanly.
- About $0.004 per 1,000 lines; on its benchmark that is 46× cheaper than Claude Haiku 4.5 and 170× cheaper than Claude Sonnet 5.
- The benchmark's mean F1 is 0.90 against 0.87 for Claude Haiku 4.5 and 0.95 for Claude Sonnet 5.
- Supports -v, -n, --score, and --json, batches 20 lines per request by default, and can keep four requests in flight.
- --explain sends up to 200 selected lines to Claude through OpenRouter for a 3-5 sentence root-cause summary.
Quickstart
bash
uv tool install jevgrep-cli
export OPENROUTER_API_KEY=YOUR_API_KEY
tail -f server.log | jevgrep "This line reports a real error, not routine noise"Watch out
MIT-licensed. Its benchmark is one hand-labelled 195-line synthetic log labelled by the author, each LLM ran once, and every judged line goes to TypeSafe or OpenRouter, so no input stays local.
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
18GitHub stars
A sort CLI where the key is a plain-English description: Jev compares texts in pairs, jsort fits a Bradley-Terry scale to the answers, and prints each score with a standard error.
Tools & Integrations#community#python#cli
Communityjsort
From the community
Posts from builders shipping with Jev right now.
A playable 16-judgment demo
AI multiple choice, not essay writing
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
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