Karpathy's llm-wiki: a pattern for building personal knowledge bases with LLM agents
stochasticchasm · x · 2026-11-12
Karpathy published "LLM Wiki" on GitHub Gist — a pattern for building personal knowledge bases using LLMs. It ships as an idea file meant to be pasted directly into your LLM agent (Codex, Claude Code, OpenCode, etc.), with the agent fleshing out specifics collaboratively.
Core idea: most people's LLM-plus-documents experience is RAG — upload files, retrieve relevant chunks at query time, generate answers. That works, but Karpathy proposes organizing knowledge as an actively maintained wiki that agents help build and curate over time, instead of only retrieving at query time. The gist already has 5,000+ stars.
More from coding & agent
- Emulating Humanlike Mouse Moves and Key Timing to Make Agents Undetectable — Darpinian · 2026-11-12
- Stanford NLP course's best homework: build your own agent harness — stanfordnlp · 2026-11-12
- Anthropic details agent memory: dreaming organizes Claude's memory, wiki+search hits 61% — RLanceMartin · 2026-11-12
- Talk preview: scaling 1,000 Fable 5.2 agents to formalize Fermat's Last Theorem — RLanceMartin · 2026-11-12
- Why Real Consumer PCs Are the Only Unblockable Way to Run Computer Use Agents — Darpinian · 2026-11-12
- Opinion: AI infra is becoming a coding runtime as intelligence units outgrow tokens — prateekj · 2026-11-12