Back
browseragentsOpen source

jev-turbo

Choose browser actions from named page controls and check whether a goal is done.

What Jev decides

Which visible control or navigation action to use next, and whether the goal is met.

jev-turbo turns visible controls into a bounded action list. Jev selects the next action and judges completion; the tool runs the action and records each step.

CHOICENOUL
Jev role
Select the next bounded browser action and assess goal completion.
Input
The goal, named visible controls, current page state, and supplied text values.
Output
An action Choice and a completion probability.
Decision frequency
Once per browser step.
Fallback
Use only supplied text; unsupported page surfaces are outside the loop.
Author reported · Source reviewed

How it works

Input
The goal, named visible controls, current page state, and supplied text values.
Jev
CHOICE + NOUL
Output
An action Choice and a completion probability.

Overview

jev-turbo uses sightmap to describe visible page controls as named candidates. Jev chooses a candidate or a navigation action and answers whether the goal is complete. The browser loop executes the choice and observes the next page. Text to type must be supplied in advance; an optional planning mode can use Claude to prepare it.

The repository compares runs with and without the site map and includes run files. These are author-reported tests on selected sites, not a general browser reliability guarantee. Canvas, frames, and file uploads are outside the documented loop.

Language
Go
License
MIT
Author
sightmap
Sources checked Sep 23, 2026

Sources

Related projects