Browser Use's Jev Ultrafast Cuts Browser Agent Costs 90% With Indexed DOM Actions
Browser Use released Jev Ultrafast, a tiny open source browser agent that books a Google Flights search in 7 seconds for under half a cent.
- Browser Use released Jev Ultrafast, an MIT-licensed browser agent using TypeSafe's Jev decision model.
- Completes a Google Flights search in 7.1 seconds at a cost of $0.0039.
- New indexed action space every step: model picks operation and element index, not selectors.
- Median task time dropped 25% versus baseline; browser protocol calls fell from 1,092 to 101.
- Small LLM only writes free-form text when operation is TYPE_TEXT; no screenshots in default loop.
- MVP limits: no shadow DOM, frames, canvas, uploads, or nested scrolling support yet.
Jev Ultrafast Replaces Per-Click LLM Planning With Indexed DOM Actions
Browser Use released Jev Ultrafast, a minimal, MIT-licensed browser agent built around TypeSafe’s Jev decision model. It converts each live page into an indexed set of available actions, then asks Jev to choose an operation and target. The repository’s headline Google Flights demo completes in about 7 seconds at normal playback and reports a cost of roughly $0.0039 per run.
The architecture keeps a general-purpose text model out of most control decisions. Jev handles clicks, selections, scrolling, waiting, and task completion. A small language model generates text only when the chosen operation is TYPE_TEXT.
A Fresh Action Table at Every Step
At every step, an atomic DOM snapshot captures visible controls, labels, values, and text in one browser call. Atomic collection means the fields describe the same page state. The agent turns that snapshot into a numbered table such as:
[1] button Change ticket type - Round trip
[2] combobox Where from? - San Francisco
[3] combobox Where to? - empty
[4] textbox Departure - emptyJev’s action vocabulary is limited to CLICK, TYPE_TEXT, SELECT, SCROLL_UP, SCROLL_DOWN, WAIT, DONE, and BLOCKED. Each target index refers to a control present in the current snapshot, and the runtime retains a reference to the corresponding DOM node.
This story is for Pro members
You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.
Comments
