
Andrej Karpathy shares the "LLM Wiki" design pattern, where an AI agent actively maintains and organizes a user's knowledge base.
The "LLM Wiki" is a design pattern introduced by Andrej Karpathy to address the "memory rot" and organization challenges typical of second-brain systems. Instead of using standard Retrieval-Augmented Generation (RAG) to query a chaotic directory of notes, the pattern proposes a three-layer architecture: raw sources, a synthesized wiki of interlinked markdown files, and instructions for how the AI agent should maintain it. Under this pattern, the LLM acts as an active gardener of the wiki—synthesizing new info, identifying connections, and resolving contradictions—resulting in a compounding knowledge base.
This pattern represents a shift from passive AI search tools to proactive AI co-workers that actively manage personal knowledge.
- –Replaces complex RAG architectures with clean, human-readable markdown wikis optimized for agent reasoning.
- –Eliminates "memory rot" by shifting the burden of categorization, linking, and deduplication from humans to AI.
- –Integrates seamlessly with agentic tools like Claude Code and Cursor to act as a navigable working memory.
DISCOVERED
3d ago
2026-06-13
PUBLISHED
3d ago
2026-06-13
RELEVANCE
AUTHOR
Av1dlive