LLM Wiki
A pattern for using Claude to build a living Wikipedia about any topic by maintaining a raw folder of source documents and a wiki folder that Claude automatically updates with interconnected pages and cross-references
As defined in Every Claude Code Memory System Compared (So You Don't Have To)
Other definitions
A knowledge management system where an LLM (large language model) automatically organizes raw source documents into interconnected markdown files with index pages and relationships, serving as a persistent, queryable knowledge base
Andrej Karpathy Just 10x’d Everyone’s Claude Code
Where it comes up · 4
- Andrej Karpathy Just 10x’d Everyone’s Claude Code7 claims
- Every Claude Code Memory System Compared (So You Don't Have To)6 claims
- Google's OKF: Why a Folder Beats the Vector Database4 claims
- Karpathy's LLM Wiki Goes Further Than Everyone Realised2 claims
Most important claims · 10 of 19Search all claims for “LLM Wiki” →
- The setup for the Karpathy LLM wiki requires only 5 minutes and does not need a fancy vector database, embeddings, or complex infrastructure—it is literally just a folder with markdown files.Andrej Karpathy Just 10x’d Everyone’s Claude Code
- The Karpathy LLM wiki method has near-zero cost (only token costs for querying) versus traditional RAG which incurs ongoing compute and storage expenses.Andrej Karpathy Just 10x’d Everyone’s Claude Code
- Normal AI chats are ephemeral and knowledge disappears after the conversation, but Karpathy's LLM wiki method makes knowledge compound like interest in a bank because it is persistent and organized.Andrej Karpathy Just 10x’d Everyone’s Claude Code
- Andre Karpathy's LLM Wiki pattern uses two folders (raw for source documents, wiki for Claude-owned output) with plain markdown files, where Claude reads from raw but never writes to it, and maintains the wiki structure and cross-references automatically without user intervention.Every Claude Code Memory System Compared (So You Don't Have To)
- Recall is a hosted service that automates Carpathy's LLM Wiki pattern, installing as a browser extension to save articles and podcasts without requiring Obsidian setup, with built-in AI chat and MCP accessEvery Claude Code Memory System Compared (So You Don't Have To)
- In spring (implied to be 2024), Andrej Karpathy, co-founder of OpenAI and former head of AI at Tesla, proposed an alternative approach called the LLM Wiki using plain text files organized in folders rather than vector databases, and this approach worked better than the industry standard.Google's OKF: Why a Folder Beats the Vector Database
- Recall has three primary disadvantages compared to Carpathy's LLM Wiki: (1) data lives on Recall's servers, not owned by user, (2) designed for content consumption, not operational memory (e.g., can find 'which video discussed X' but not 'what did we decide about client Y in March'), and (3) carries pricing implicationsEvery Claude Code Memory System Compared (So You Don't Have To)
- The LLM wiki method finds information by reading indexes and following links rather than using similarity search, providing deeper understanding of relationships through explicit connections rather than semantic similarity.Andrej Karpathy Just 10x’d Everyone’s Claude Code
- The Karpathy LLM Wiki framework involves a three-level structure: raw data ingestion, summarization and structuring of data, and schema creation that tells the AI where data is stored and how to access it, enabling knowledge base growth without loss of maintainability.Karpathy's LLM Wiki Goes Further Than Everyone Realised
- The LLM Wiki inverts RAG by building knowledge once upfront into a folder of interconnected plain text files rather than re-deriving everything at query time, creating a living encyclopedia that models can read the way developers read a code base.Google's OKF: Why a Folder Beats the Vector Database