CalibratedDecisions.

Repo · Agents & browsers

GUI JEV Harness

Python harness for GUI grounding: it divides a screenshot into grid tiles, has a vision model describe each tile neutrally, then asks typesafe-ai/jev…

Open github.com ↗

From the repository

Fast GUI Grounding with jev

How builders describe it

Python harness for GUI grounding: it divides a screenshot into grid tiles, has a vision model describe each tile neutrally, then asks typesafe-ai/jev to choose among the descriptions. Local confidence and margin gates decide whether to descend or refuse, and it emits only a point and bounding box.

The decision Jev makes

Pick the next click, field or navigation from the legal actions on screen.

Where it fits

Browser agents need to choose an action on every step. With Jev each step is a choice from the actions actually available on the page, which keeps agents fast and on the rails. All 299 agents & browsers projects →

Related projects