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
Jev Arena
A comparison arena that runs the same batch of review comments through Jev and DeepSeek, showing processing time, cost, and per-label results with CSV/Excel import, replay, and offline reports.
- Category
- Practices & Patterns
- Published by
- Community
- Author
- NanmiCoder
- Added
- 2026-09-22
Tagscommunityjavascriptbenchmarksevaluationdataopenrouter
Highlights
- On 10,000 reviews Jev took 203.2 s and about $0.84 versus DeepSeek Flash at 823.5 s and an estimated $1.50.
- Under GPT-6 Astra review, all three labels (relevance, sentiment, intent) were correct together for 62.69% of Jev rows versus 67.26% for DeepSeek.
- The README states the accuracy check used an AI reference rather than a human gold standard, and that strict first-choice scoring gives 50.58% and 55.45%.
- Runs need Node.js 22+ and OpenRouter plus DeepSeek keys; replays call no models and reports can be generated offline.
Quickstart
bash
git clone https://github.com/NanmiCoder/jev-arena.git
cd jev-arena
npm ci
npm startWatch out
MIT-licensed for the code, while demo comments belong to their original authors and platforms. Needs Node.js 22+ and OpenRouter and DeepSeek keys; results describe this one dataset and configuration.
More like this
104GitHub stars
A personal-assistant agent with 100 mocked tools that measures how many steps a task takes when the LLM picks the tool versus when Jev picks it before every model step.
Practices & Patterns#community#typescript#agents
Communityjev-eval-agent
208GitHub stars
A self-hosted implementation of TypeSafe's Jev System One API powered by the 400M-parameter GLiFormer encoder: it serves choice, score, and noul and drops into the official typesafe-sdk via TYPESAFE_BASE_URL, but trails Jev on reasoning-heavy tasks.
Practices & Patterns#community#python#open-models
Communityjeff
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