Full Jev Tutorial What it is, how you can build with it and what new applications it can unlock → 0:00 Intro → 0:34 Jev explained → 4:06 API setup → 5:59 Demo 1: Voice-controlled browser → 11:33 Demo 2: AI memory → 17:27 Demo 3: YouTube predictor
jsort
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.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- keltokhy
- Added
- 2026-09-22
Tagscommunitypythonclirerankingsearch
Highlights
- On 51 FOMC sentences it made 255 comparisons in 10 rounds with reliability 0.96 and first-position lean -0.07, costing $0.0037 in 7.2 seconds.
- Across 95 opening statements the top four were 2022 hikes of 75 points; per-chair averages ran from -2.19 for Bernanke to 2.32 for Warsh.
- It asks about a few pairs per text rather than all of them, and a scale records the model that answered it.
- A thousand short lines take about 5,000 comparisons, roughly a minute and seven cents; -r prints the other end from cache.
- All the JevKit tools share ~/.cache/jev/answers.sqlite, keyed by provider, endpoint, model, text, and question.
Quickstart
bash
uv tool install jev-sort
export TYPESAFE_API_KEY=YOUR_API_KEY
jsort -o "more hawkish about inflation" presser.txt | head -6
jsort -r "more urgent" tickets.txt | headWatch out
MIT-licensed. Needs Python with uv and a TypeSafe, OpenRouter, or gateway key; the budget defaults to $1.00, the standard error treats anchors as exact, and a price rise can push spending past the limit.
More like this
2.6kGitHub stars
A cross-platform memory layer for AI coding agents: conversations from Claude Code, Codex, DeepSeek Harness, OpenClaw, and OpenCode become Markdown memories indexed in Milvus, with optional Jev reranking through the TypeSafe API.
Tools & Integrations#community#python#agents
Communitymemsearch
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
From the community
Posts from builders shipping with Jev right now.
Full Jev video tutorial
The case against Jev-scored compaction
This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the Show more
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
Classifying rows in DuckDB
I made a DuckDB extension where you can use @typesafeai 's Jev to do quick classification of rows in any csv/parquet file or duckdb table about 10sec for 1k rows ~ better than using an LLM, way more ergonomic than a classifier game-changing for data analysis!
A playable 16-judgment demo
typesafe's jev is fun! live demo you can play with: typesafe-demo.val.run
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