Ask Jev anything. Give it a try at askjev.ai It won't answer. It will judge. Let's see if we can get to 1 million questions. @typesafeai 🤝 @convex work great together. @hmartenjoyer @CompleteSkeptic @justKDeng @mikeysee
Jev Reranker
A CLI that reranks, filters, or extractively compresses JSON retrieval results by asking Jev separate Noul questions, then lets Rust apply the order and thresholds, reading stdin and writing stdout.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- shinpr
- Added
- 2026-09-22
Tagscommunityrustclirerankingsearch
Highlights
- Three modes: rerank orders by a 0-to-1 rerankScore, filter drops candidates without usable evidence, and compress keeps relevant sentences or lines.
- Field mapping flags select the text field and a context field, while IDs, source paths, and retrieval scores pass through unchanged.
- Rerank and filter make one sequential request per 30 candidates by default; compression scores every sentence or line and can need more requests.
- Filter keeps candidates with evidenceScore >= 0.5 in input order by default, and --threshold accepts 0 to 1.
- Retries 429 and 529 responses up to twice after 250 ms and 500 ms waits; other errors are not retried.
Quickstart
bash
npm install --global jev-reranker
export TYPESAFE_API_KEY="YOUR_API_KEY"
printf '%s\n' '[{"text":"Build artifacts are cached locally."},{"text":"Access tokens expire after one hour."}]' | jev-reranker --query "How long do access tokens last?"Watch out
MIT-licensed. Needs Node.js 14+ and a TYPESAFE_API_KEY; each invocation makes its own API requests, --top does not reduce API work, and long documents can send repeated copies of context in compression batches.
More like this
32GitHub stars
A Rust CLI and MCP server that reranks live DuckDuckGo SERPs with Jev and audits SEO/GEO readiness (schema, robots.txt, sitemaps, llms.txt) with a fifty-rule engine, no paid SEO subscriptions, and a local SQLite history.
Tools & Integrations#community#rust#cli
Communityjev-seo
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 million judged questions
Inferring Jev's internals from 1,000 calls
Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more
The open System One roundup
Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more
Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格
The launch post
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 Show more
Trading bot, one decision per block
I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app
Classifying 1,500 real emails
this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away
@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