All-Hands-AI
Frontend: Implement browser tab
In the actual Devin demo there is a browser tab that allows the user to see which pages the assistant is currently looking at. But we do not have such a tab within our current prototype frontend.
We could add such a tab. Contributors for this welcome!
I would like to work on this issue, could you please assign this task to me!!
If the assistant views webpages through Selenium, it can send a screenshot every second (or every page update) to the frontend, which this tab can render.
Embedding an <iframe /> is also possible but might have security/reliability issues (such as CORS).
Yeah, I think that the selenium screenshot might be the appropriate way to do things here, nice idea @yimothysu !