felipesabino

But I wanted even less interaction with most websites, as most of the headlines are related to something I am just mildly interested on, to the point of wanting to know more, but not interested enough to the point I feel like committing to reading the whole thing before knowing a bit more what it is about.

Anyway, I build this thing that parses the RSS feeds and do all summaries locally through ollama or whatever other OpenAI API compatible llm platform you have (e.g. LM Studio), and auto updates automatically twice a day through GitHub action scheduler

Last time I had contact with them, they were exploring using Plasmo [1] as building block for the extension, instead of doing everything vanilla as they did in the 1st version, which would offer cross-browser support out of the box.

But meanwhile, you can check the code [2] and add the FF manifest yourself to try it out.

And I strongly suggest that you contact Kay Xu <[email protected]>, who is doing research on sensemaking [1] [2] and berrypicking [3], I think he is currently working on newer and better version of his approach with browser extensions (as opposed to a separate renderer), and you both would benefit from collaboration.