X post · by Milind S

Computer use without screenshots

On-device segmentation and OCR turn the screen into text for Jev.

Milind S

@milindlabs

Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets. It returns a probability across those elements and tells me the best one to click. Then it clicks, re-runs detection, and decides again. In a loop until the goal is done. ~90ms per decision. Faster than any LLM computer use I've tried. Blazing fast computer use, without any latency @typesafeai is building something really interesting

Sep 17, 2026 · 1.4K likesOpen on X

Milind S runs computer use on a Mac without sending screenshots anywhere. A local CoreML model finds every button and UI element on screen, on-device OCR reads the labels, and that text is all Jev gets.

Open the source

jev-ultrafast

Browser Use’s browser agent, with Jev choosing each next step.

Browser Use

~2.9k

Gregor Zunic

@gregpr07

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 ↓

X postAgents and browsers

Pick

Flight search with Browser Use

Run time: ~7 s
Cost: ~$0.004

Kyle Jeong

@kylejeong

we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand executes it.