Agents crawling nostr through similarly related content, without relying on a centralized db #Alexandria's gonna have that ๐Ÿ˜‰
liminal ๐Ÿฆ 's avatar liminal ๐Ÿฆ 
Still very much a demo, but now here it is. AI + Nostr: 1) Text search on the title + author of a note 2) Semantic search on content Example: "The cat chased the mouse" is semantically similar to "Felines hunt their prey at night" even though they don't have any words in common. What this means is that you don't need an exact match of the text, you just need to type in words you think are related and it will retrieve the K closest events that are "semantically similar" View quoted note โ†’
View quoted note →

Replies (3)

Still prototyping the AI stuff, you can find our client here https://next-alexandria.gitcitadel.eu/ If you know Obsidian, the visualization tab hints at where we're going with this & AI. Its going to be renamed to "navigator" Just recently revamped our look!
GitCitadel's avatar GitCitadel
Hello. We have a new feature implemented, in #Alexandria, which might interest some of you. We have revamped and expanded the index card menu. You now have the ability to display publication details (index metadata) on the cards, including book summaries, ISBNs, and links to the npub profile pages of the publishing npub and the author. (If the author has a npub and is referenced in the 'p' tag, as with @Gigi's book, below.) image This allows for publisher and author to share in the credit and the zaps, and to both be notified of interactions with the index. You also have the ability to open an original URL-source of the publication (usually to a web page, PDF, LaTeX file etc.), even if the publication is also available in event form. Currently, it opens outside the app. This opens up Alexandria to being a true library catalog of all publications, even those under copyright or where there is no digital version readily available. They can be referenced and interacted with, through the index cards, in a manner similar to GoodReads or other "book review" sites. This will become more apparent, once we add things like kind 1111 comments, to the index events. For now, we're still revamping the parser and the table of contents, but they should be replaced #thoon. Thank you for your patience and support, while we rebuild, and may you have a good evening. Happy reading! https://next-alexandria.gitcitadel.eu/
View quoted note →
You won't need to vibe #Alexandria into existence and end up with a buggy, incoherent mess. All it would be doing is scraping our code and turning it into a sloppy, spaghetti version, with the color scheme you requested. And, since you and I know each other, we both know that it will be orange ๐ŸŠ spaghetti. We are going to provide you with a free, tailor-made, AI-powered workflow, which will help you fork, customize, and install your very own version of our FOSS software (which includes the fastest upload-relay on the market and integration of your community relay), and ensure that you can continue to update that version with new features we add to the main one. We will help you support it, there will be real humans on the other end of the line, and our C++ NDK will be underlying it all. Do not settle for vibing. AI is bigger than that. We are going to AI all the things. image View quoted note โ†’
โ†‘