Browser Use 团队基于最近爆火的 Jev 模型做了个 jev-ultrafast，主打就是快，已经狂揽了 19000+ Star。
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Browser Use 团队基于最近爆火的 Jev 模型做了个 jev-ultrafast，主打就是快，已经狂揽了 19000+ Star。 官方给的演示案例里，在 Google Flights 上搜苏黎世飞伦敦的航班只用了 7.1 秒。 它把页面上能点的按钮、输入框编成一张带编号的表，Jev 一次请求就同时决定做什么动作、点哪一个元素。 只有需要往框里打字时，才叫一个小模型生成文字。默认流程里也不截图，全靠读页面结构。 GitHub：http://github.com/browser-use/jev-ultrafast 作者拿新旧两版各跑了三轮同一个任务，耗时中位数从 9.45 秒降到 7.09 秒，跟浏览器的通信次数从 1092 次降到 101 次。 模型的输出不会直接变成点击坐标或者脚本，只能从页面上真实存在的元素里挑，这个设计挺让人放心。 核心代码就 6 个文件，想弄明白浏览器 Agent 到底怎么跑起来的，感兴趣的开发者可以看看。
Posted by GitHubDaily (85.4k followers) 1 h ago · 21 likes · 2k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: jev-ultrafast.
More dev work like this
- There are some new top models leading our code review benchmark. — @Macroscope
- Day 1 of @WeAreDevs is a wrap! — @pamelafox
- Your agent was asked to export a file. It also wrote a checksum nobody uses. — @DanKornas
- Few interesting changes in 18.3.0: — @_can1357
- Nothing in the world could have prepared me for the root cause of the performance issues… — @theo
- Pipelex executes typed AI procedures declared in .mthds files. — @tom_doerr
- Google Antigravity SDK now runs Gemma 4 26B locally on GPU via Google AI Edge LiteRT. — @0x0SojalSec
- MiniMax H3 跑视频，最磨人的有时候不是生成，而是 VAE 解码太慢。 — @bkdgiffug
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 23.1k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 01:40 UTC. Full method.