CONTROLAgents & automation
Jev Browser Agent
Benji@boiopollo
0:36This project demonstrates a browser agent built with a local LLM and Jev by TypeSafe AI, capable of performing tasks like navigating Google Maps and retrieving directions by controlling browser actions.
ok this is wild
I think browser agents are about to get a lot cheaper.
I've been playing around with Jev by TypeSafe AI and built a small browser agent with:
Local LLM + Jev + browser control.
I ask it to get me directions on Google Maps.
It opens Maps.
Searches the destination.
Clicks through the UI.
Gets the route.
The interesting bit isn't Google Maps.
It's that you don't need a huge frontier model reasoning over every tiny browser action.
The local model handles the broader task.
Jev handles the fast decisions.
And suddenly you've got something that's ridiculously fast and ridiculously cheap to run.
I think this is where a lot of agent architecture is heading:
Big models for the hard stuff.
Small, specialised models for the hundreds of tiny decisions in between.
More playing around to do - but this combination is pretty damn fun.
Demo below 👇