LLM Wiki

LLM Wiki, created by Andrej Karpathy, is a community-maintained knowledge base for LLM engineering that uses iterative AI refinement instead of traditional RAG for managing information.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.