Jev in production › Agent tool and action selection
Browser agent that indexes each page into candidate controls and has Jev pick the next action, while an LLM plans and reads and code gates secrets and irreversible clicks. It passed 41/42 tasks against 39/42 for the Browser Use agent (author).

A browser agent that picks from the controls a page actually has, cites the page for every claim, and keeps credentials, irreversible actions and spending under the control of code.
- It picks, it does not invent. Each page is indexed into the controls it has, and Jev, a choice model, picks one. It cannot click something that is not on the page, and there are no selectors to maintain. Widget keyboard actions are chosen from the keys their ARIA roles define. - Answers you can check. Every claim in a complete answer cites a verbatim quote from the page, with a link that scrolls to it. Pass a schema and get validated data back. Tasks over a whole list can follow its next-page links, checking each page and preserving its citations. - Code holds the...
For the project's own README, linking back here: