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 ↓
Browser Use Ultrafast with Jev
Browser Use's Ultrafast agent puts Jev in charge of picking each browser action from a dynamic DOM action space. The author reports a flight search in 7 seconds for about $0.0039.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- Gregor Zunic
- Added
- 2026-09-20
The post
Tagscommunityxvideobrowserdemo
Highlights
- Next-action choice moves to Jev, with a new action space computed each step.
- The demo video runs at 1x speed; a Google Flights search took 7 seconds for $0.0039.
- A small LLM is kept only for typing text.
- Open-source agent from the Browser Use team.
Watch out
A single author-reported run; no reproducible benchmark is linked.
More like this
The pg-jev author demos jev(), a PostgreSQL extension that filters table rows with natural-language conditions and no index or embeddings, judging 129 rows in about a second.
Tools & Integrations#community#x#video
Community
A short demo of a model router built with Jev: each request is classified by Jev and forwarded to the model judged most suitable, shown as a screen recording.
Tools & Integrations#community#x#video
Community
Kyle Jeong's demo of browser use with Jev and Stagehand: the accessibility tree is the state, actions are the questions, and one remote-browser task cost $0.001 at near-instant speed.
Cookbooks & Demos#community#x#video
Community
From the community
Posts from builders shipping with Jev right now.
Vercel's fx safety reviewer, 18x faster
We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.
@fazxes
We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice
Jev lands on OpenRouter
Jev by @typesafeai is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate Show more