Skip to content
Tech News
← Back to articles

Show HN: Atomic – Self-hosted, semantically-connected personal knowledge base

read original get Atomic Knowledge Base → more articles
Why This Matters

Atomic introduces a self-hosted, AI-augmented personal knowledge base that transforms markdown notes into a semantically-connected knowledge graph. Its features enable users to organize, search, visualize, and synthesize their notes efficiently, leveraging advanced AI capabilities. This innovation empowers consumers and professionals to better manage and utilize their personal information in a privacy-conscious environment, fostering more intelligent knowledge management.

Key Takeaways

Atomic

A personal knowledge base that turns markdown notes into a semantically-connected, AI-augmented knowledge graph.

Atomic stores knowledge as atoms — markdown notes that are automatically chunked, embedded, tagged, and linked by semantic similarity. Your atoms can be synthesized into wiki articles, explored on a spatial canvas, and queried through an agentic chat interface.

Features

Atoms — Markdown notes with hierarchical tagging, source URLs, and automatic chunking

— Markdown notes with hierarchical tagging, source URLs, and automatic chunking Semantic Search — Vector search over your knowledge base using sqlite-vec

— Vector search over your knowledge base using sqlite-vec Canvas — Force-directed spatial visualization where semantic similarity determines layout

— Force-directed spatial visualization where semantic similarity determines layout Wiki Synthesis — LLM-generated articles with inline citations, built from your notes

— LLM-generated articles with inline citations, built from your notes Chat — Agentic RAG interface that searches your knowledge base during conversation

— Agentic RAG interface that searches your knowledge base during conversation Auto-Tagging — LLM-powered tag extraction organized into hierarchical categories

... continue reading