An AI zettelkasten that extracts ideas from articles, videos, and PDFs
Details
- External ID
- 46110897
- Source
- HN
- Company
- —
- Product
- An AI zettelkasten that extracts ideas from articles, videos, and PDFs
- Website domain
- github.com
- Launched
- Dec. 1, 2025
- Cohort
- —
- Upvotes
- 38
- Upvotes percentile
- 0.7767175572519084
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
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/W7ejMqZ6EUQRepo: https://github.com/schoblaska/jargonYou 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.
Enrichment
- Theme
- browser automation and scraping for AI
- Vertical
- Horizontal
- Function
- Content generation
- Audience
- Prosumer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- ai zettelkasten that extracts ideas from articles, videos, and pdfs
- Manually corrected
- False
Could you build this?
Yes Jargon is an LLM-assisted knowledge graph application built by scraping text/transcripts, passing them to LLM APIs for concept extraction, and saving notes and relationships to a local markdown or graph database.
Discussion
9 comments analyzed.
Competitors mentioned: Traditional Zettelkasten implementations, Literature note-taking tools
Concerns raised: Removes the core manual thinking/connection-making that defines Zettelkasten, LLM substitution undermines the personal knowledge synthesis aspect, Misses permanent notes requirement (user's own ideas, not extracted summaries), Requires external API connection/OpenAI dependency
Feature requests: Full text search functionality for discoverability, Support for offline operation without external APIs, Integration of user's own notes/thoughts alongside collected content
Competitors
Other products that read as similar to this one — 41 launches clear the similarity bar, closest 8 shown.
Attention rank: #7 of 42 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 20 days after the earliest competitor.
- PDFStream AI · ph · 2026-09-17 · 1 upvotes · similarity 0.38
- Kerns, an AI interface to understand anything, better than NotebookLM · hn · 2025-11-11 · 7 upvotes · similarity 0.37
- DiffFind · ph · 2026-09-27 · 2 upvotes · similarity 0.37
- WikiCrawl · ph · 2026-09-28 · 1 upvotes · similarity 0.36
- Training a model to identify AI web content from structure alone · hn · 2026-09-22 · 73 upvotes · similarity 0.36
- Coherence · ph · 2026-09-18 · 1 upvotes · similarity 0.36
- Summa, a tool that annotates over whatever you're reading · hn · 2026-07-15 · 5 upvotes · similarity 0.35
- WikiNow · ph · 2026-09-10 · 1 upvotes · similarity 0.35
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a content generation tool for Government yet.