Show HN: An AI zettelkasten that extracts ideas from articles, videos, and PDFs

Posted by schoblaska 8 days ago

Hey HN! Over the weekend (leaning heavily on Opus 4.5) I wrote Jargon - an AI-managed zettelkasten that reads articles, papers, and YouTube videos, extracts the key ideas, and automatically links related concepts together.

Demo video: https://youtu.be/W7ejMqZ6EUQ

Repo: https://github.com/schoblaska/jargon

You can paste an article, PDF link, or YouTube video to parse, or ask questions directly and it'll find its own content. Sources get summarized, broken into insight cards, and embedded for semantic search. Similar ideas automatically cluster together. Each insight can spawn research threads - questions that trigger web searches to pull in related content, which flows through the same pipeline.

You can explore the graph of linked ideas directly, or ask questions and it'll RAG over your whole library plus fresh web results.

Jargon uses Rails + Hotwire with Falcon for async processing, pgvector for embeddings, Exa for neural web search, crawl4ai as a fallback scraper, and pdftotext for academic papers.

Comments

Comment by jasonpeacock 8 days ago

This is neat, but it's not zettelkasten - it's building a browse-able knowledge DB from content.

Zettelkasten is about about writing down your ideas in response to content, with a link to that content, and then linking to other ideas that your already logged. It's not an extraction of ideas from that content. This is a common mis-understanding of zettelkasten.

Comment by windows_hater_7 8 days ago

I’ve thought about something like this, but I feel like the core part of the Zettelkasten method is the act of making connections and extracting ideas from the sources you interact with.

Comment by ta988 8 days ago

It removes the most important part of Zettelkasten: You

Comment by dSebastien 8 days ago

True

Comment by afarviral 3 days ago

Very cool. I was thinking about something similar. In response to those saying it is not in the true spirit of Zettelkasten, that's probably fair, but this could easily incorporate your own notes/thoughts too, but you get to keep a convenient summary of the content you collected from outsite yourself. I think the other commentors may have missed the fact that while the LLM substitutes you, it does try to create new insights during the "Thread" part of the core loop.

Comment by dSebastien 8 days ago

It seems like a useful research tool, but it doesn't have much to do with zettelkasten. At best it helps creating literature notes, but permanent notes are always yours to write since they're about your own ideas, your own thinking, etc.

https://www.dsebastien.net/2022-05-01-zettelkasten-method/

Comment by frankhsu 8 days ago

I love this concept, an AI-managed zettelkasten that actually closes the loop back into new sources. As the TODOs in end of your repo, I just humbly suggest that make "full text search" the top priority,enhancing discoverability and trustworthiness.

Comment by badmonster 7 days ago

Does this tool work offline or does it require an API connection to external services like OpenAI?

Comment by badmonster 7 days ago

[flagged]