Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓
AI CLI
Vercel Labs' terminal CLI for the AI SDK: its `ai evaluate` command answers named Boolean, Choice, and Score questions, with Jev as the default evaluation model and one unchanged input shared across all questions.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- vercel-labs
- Added
- 2026-09-22
Tagscommunitytypescriptclievaluationvercel
Highlights
- `ai evaluate` takes repeatable --boolean, --choice, and --score flags or a named question map in JSON; Jev is the default evaluation model.
- Stdin maps to the SDK's state and typed flags build the named questions; with --json, stdout carries only metadata.
- Boolean returns P(true) from 0 to 1, Choice returns one supplied option plus its distribution, and Score uses Jev's probability-weighted mean.
- Requires Node.js 22+ and an AI Gateway API key or a provider key; evaluate requests time out after 30 seconds by default.
- The same binary generates text, images, video, and audio, supports piping between commands, and exits 2 on partial generation failure.
Quickstart
bash
npm install -g ai-cli
cat ticket.txt | ai evaluate \
--boolean "refund=Refund requested?" \
--choice "team=Which team?" \
--choices "team=billing,support" \
--score "tone=How positive?" \
--levels "tone=angry,neutral,happy"Watch out
The README states Apache-2.0 though the digest lists no license file; it needs Node.js 22+ and a Vercel AI Gateway key (or a provider-specific key), and question limits are enforced by the SDK and provider.
More like this
17GitHub stars
A CLI that grades markdown and text files against plain-Markdown rulesets with Jev, running every rule against every line in parallel and caching unchanged lines to avoid repeat API calls.
Tools & Integrations#community#typescript#cli
Communityslop-grader
392GitHub stars
A staged code-review workflow that uses Jev for bounded judgments over Git diffs or whole codebases, with a local dashboard. Policy and thresholds stay in code while Jev screens five risk areas.
Tools & Integrations#community#typescript#code-review
Communityjev-review
From the community
Posts from builders shipping with Jev right now.
Browser Use Ultrafast, powered by Jev
A really smart switch statement
hype-free explanation of jev: jev does not replace gpt / claude jev is just a *really* smart switch statement like if 2016 ml classifiers got 2026 levels of intelligence it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate * = and by Show more
@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
When a designer gets Jev
when a designer gets access to Jev
Full Jev video tutorial
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
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!
