Skip to content

Karpathy's LLM Wiki - Full Beginner Setup Guide

Summary

A step-by-step video tutorial by Teacher's Tech (Jamie) building an LLM Wiki from scratch using Obsidian and Claude Code, using a "planning a trip to Japan" demo scenario.

Key Takeaways

Three-Layer Architecture Explained for Beginners

  1. Raw Sources — PDFs, articles, meeting notes; read-only for the AI; source of truth
  2. The Wiki — Markdown files the AI creates and maintains: index page, concept pages, entity pages, summary comparisons, all interlinked
  3. The Schema — Rules document (CLAUDE.md for Claude Code) telling the AI how to structure the wiki, handle new sources, and format everything

Schema File Contents

The CLAUDE.md/AGENTS.md schema should specify: - Purpose — what the knowledge base is about (one line to customize) - Folder structure — where raw resources and wiki output live - Ingest workflow — read document → extract key concepts → create/update wiki pages → update index → log changes - Page formatting rules — summary at top, source references, links to related concepts - Question answering behavior — consult wiki first, cite sources, flag uncertainty

Setup Walkthrough

  • Created raw/, wiki/, templates/ folders in Obsidian vault
  • Dropped CLAUDE.md schema into project root
  • Used Obsidian Web Clipper to save a Tokyo travel blog as markdown into raw/
  • Claude Code ingested the source in ~3 minutes, creating structured wiki pages for neighborhoods, temples, etc.
  • Added a second source (Japan food guide); Claude updated existing neighborhood pages rather than just creating new ones — demonstrating the compounding effect
  • Graph view showed more nodes and connections after the second ingest

Cross-Source Query Demo

Asked: "What neighborhood should I stay at if I want to be close to the best food and still near the major temples?"

Claude pulled from neighborhood pages, food pages, and temple pages — connecting dots spread across completely different sources, citing specific wiki pages. This is fundamentally different from basic RAG.

Linting Demo

Prompt: "Please lint the wiki."

Claude returned a report checking: orphan pages, broken links, structural soundness, citation issues. Identified the biggest gap as an uningested food source and offered to fix citation issues.

Use Cases Mentioned

  • Students/researchers — wiki as you read papers; structured knowledge base instead of highlighted PDFs
  • Teachers — feed curriculum documents, PD materials; personal teaching wiki that grows
  • Businesses — meeting notes, customer calls, project docs; new team members browse wiki instead of Slack history
  • Curious readers — track learning from books, podcasts, articles; personal encyclopedia

Limitations Stated

  • Best at personal scale (~100 articles); tens of thousands of pages needs more infrastructure
  • Garbage in, garbage out — sources must be curated
  • Requires a coding agent (Claude Code, Codex, or similar); Obsidian alone doesn't do this
  • AI can make mistakes (miscategorization, wrong connections) — linting is essential