Marginalia Site Explorer Rabbit Hole Generator

I've been a bit obsessed with the idea of flipping through the internet a bit like you would a magazine, of undirected browsing as a discovery mechanism, and I think I'm approaching something that's beginning to feel pretty fun. The link at the top will return results out of a pool of approximately 10,000 domains, you can refresh to get new ones. You can also explore in a directed fashion by using the 'Similar Domains'-buttons. These are not random. A sampler, beyond the random sites offered with the head link https://search.marginalia.nu/explore/www.amiga-news.de…

A launchpad for your curiosity

I built Yourabbit.com — a site that curates hand-picked YouTube rabbit holes grouped by themes like quirky psychology, obscure tech, weird facts, and binge-worthy oddities. It’s not driven by the YouTube algorithm — every collection is themed and curated manually (for now), with a backend I’m automating to fetch and organize new rabbit holes daily. Built as a hybrid Astro + Next.js project, optimized for static generation and speed. I’m also pairing videos with custom summaries and commentary (using AI), and would love feedback from the HN crowd on: Content model (too wide? not specific…

I built this tool because I wanted a way to just take a bunch of URLs or domains, and query their content in RAG applications. It takes away the pain of crawling, extracting content, chunking, vectorizing, and updating periodically. I'm curious to see if it can be useful to others. I meant to launch this six months ago but life got in the way...

A Firefox extension to map your Wikipedia Journeys

Been messing with cosine similarity and decided to try calculating nearest neighbors over the entire link graph for the marginalia search engine. Turns out that you can just bruteforce that in a day or two. And the results are pretty good. One drawback is that depending on if you're looking at an older website, a lot of the links are dead. The deduplication isn't great either.