News for hackers. Stuff that matters.
Re:Show HN: Atomic – Local-first, AI-augmented personal know... by kenforthewin on Friday April 24, 2026 @11:14AM (#47891399)
Biggest difference is Atomic leverages an LLM to auto-tag and a text embedding pipeline to drive semantic search - so the knowledge base is self-organizing. The bet here is that having an agent grep the filesystem is fine for a carefully curated, relatively small set of markdown files. It starts to degrade if you approach your knowledge base as a place to put everything: personal notes, articles you find interesting, entire textbooks if you want to. Having a vector database in this context is pretty much required past a certain scale; a filesystem-based approach is just an incredibly inefficient way to do retrieval in this context, and your agent is bound to miss important data points.
Re:Show HN: Atomic – Local-first, AI-augmented personal know... by thomas_viaelo on Friday April 24, 2026 @01:30PM (#47893305)
Does the LLM auto-tagging and embedding pipeline run on the device, or are they remote calls?
Re:Show HN: Atomic – Local-first, AI-augmented personal know... by redrove on Friday April 24, 2026 @04:22PM (#47895283)
So an Obsidian plugin? Got it.
Re:Show HN: Atomic – Local-first, AI-augmented personal know... by kenforthewin on Friday April 24, 2026 @04:48PM (#47895579)
One can imagine an obsidian plugin of any arbitrary level of complexity, given it's written in a Turing-complete language.