A knowledge graph consists of nodes for everything one knows something about and edges for the relationships between them. Unlike a collection of links, the edges have meaning: “A builds on B” says something different from “A uses B”. A graph sorts by connection rather than by date, so older knowledge stays visible as long as other nodes point to it. The Zettelkasten follows the same idea on paper.
- Covered in
-
- Why a Graph A list sorted by date shows what is new. A graph shows what belongs together. This website needs both.
- Basis for
-
- How an LLM Wiki Works How an LLM wiki works, shown on this knowledge base: Markdown in its own Git repository, a Python tool with MCP for agents, and a website that only displays it.
- See also
-
- LLM Wiki Andrej Karpathy's pattern for personal knowledge: an LLM agent reads each source once and works it into a growing set of interlinked notes.
- Retrieval-Augmented Generation Answering questions with an LLM by first retrieving relevant passages from a knowledge store and giving them to the model as context.
- Zettelkasten A working method in which every note contains exactly one idea and is linked to other notes through references.
- Tags