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.
- 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.
How it works
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
Related projects
Jev Voice Browser
A browser that starts resolving voice commands while the user is still speaking.
What Jev decides
What the user intends, which page target it applies to, whether the command is complete, and whether it is destructive.
Jev × WebMCP
Turn WebMCP schemas and user wording into inspectable browser tool calls with typed Jev decisions.
What Jev decides
Which tool fits, which allowed value each typed parameter should take, and whether optional values were actually stated.
jev-browse
Drive a browser one Jev decision at a time through agent-browser.
What Jev decides
Click, type one supplied value, press Enter, go back, finish, or report blocked.