Open KB: Open LLM Knowledge Base
Compiled wiki beats query-time RAG with vectorless PageIndex retrieval for long PDFs.
Memoriki - LLM Wiki + MemPalace. Personal knowledge base with real memory.
LLM compiles knowledge into wiki pages instead of RAG retrieving raw chunks.
Researchers, founders, and students building second brains
Obsidian · Logseq · Mem.ai
It combines Karpathy's LLM Wiki pattern (structured markdown wiki maintained by an LLM) with MemPalace (an MCP server that adds semantic search and a temporal knowledge graph).
Three layers: - Wiki pages with [[wiki-links]] and YAML frontmatter - the LLM creates and maintains these - Semantic search via embeddings (ChromaDB) - find things by meaning, not keywords - Knowledge graph with typed relationships and date validity - "what changed since last month?"
It's not RAG. RAG re-derives answers from raw chunks every time. Here the LLM compiles knowledge into wiki pages once, keeps them current as new sources arrive, and the graph tracks how everything connects.
Works with any MCP-compatible agent (Claude Code, OpenAI Codex, Cursor, Gemini CLI).
Compiled wiki beats query-time RAG with vectorless PageIndex retrieval for long PDFs.
Multi-agent research with fuzzy routing and cross-wiki synthesis.
Karpathy's LLM Wiki pattern implemented with file storage instead of vector databases.
Git template for Karpathy's LLM wiki pattern with metadata and lint checks.
Karpathy name-drop is marketing—Obsidian, Logseq, and Mem already do LLM knowledge bases.
Knowledge compounds across videos instead of re-searching from scratch every query.