Claude-Powered Markdown Wikis Beat RAG for Personal Knowledge

Andrej Karpathy's LLM wiki uses Claude to auto-organize raw markdown into linked, indexed notes—setup in 5 minutes, handles 100 docs/500k words, cuts token use 95% vs RAG by reading relationships instead of embeddings.

Setup Claude Wiki in 5 Minutes for Compounding Knowledge

Paste Karpathy's gist prompt into Claude Code (via terminal or VS Code) to initialize a vault: creates /raw for source docs, /wiki for organized output, index.md listing concepts/entities/sources/people/comparisons, log.md for operation history, and claude.md defining project rules. Use free Obsidian as visual frontend for graph view of backlinks/tags. Drop raw content (e.g., PDFs, web clips via Obsidian Web Clipper extension set to /raw) and command Claude: "Ingest file"—it chunks into 5-25 linked MD pages per article, extracts tags/authors/takeaways, builds relationships (e.g., one AI-2027 article yielded 23 pages: 1 source, 6 people, 5 orgs, 1 AI system, multiple concepts). Batch ingest scales: 36 YouTube transcripts in 14 minutes auto-linked tools like Claude Code/WAT framework across videos, revealing patterns without manual work. Customize via claude.md (e.g., flat structure for personal brain vs subfolders like /tools/ /techniques for YouTube wiki). Patiently wait 10-14 minutes per batch as Claude reasons on granularity/focus.

Query and Maintain for Deeper Insights Than Ephemeral Chat

Claude reads full wiki/index/log for queries, following links for context (e.g., click "OpenAI" from source to related model spec/psychology pages). Auto-maintains summaries/index, identifies gaps (e.g., "Fetch articles on compute scaling"), runs "lint" checks for inconsistencies/missing data via web searches/new connections. Add hot.md cache (500 chars recent updates) for agent efficiency. Relationships compound: backlinks connect video techniques to tools, enabling pattern discovery (e.g., MCP servers across 36 videos). Token savings hit 95% on 383 files/100+ transcripts—one user query dropped from massive context to compact wiki reads. Linting ensures scalability; log tracks every update.

Outperforms RAG for Small-Scale: Simpler, Cheaper, Relational

Skip vector DBs/embeddings/chunking—markdown files alone suffice for <500k words/100 docs, as LLM navigates explicit links/index vs similarity search. RAG needs ongoing compute/storage; wiki costs only ingest/query tokens (free infra). Deeper reasoning from relationships ("OpenAI links to governance/geopolitics") beats RAG's shallow chunks. Trade-off: scales poorly beyond small wikis (use RAG for massive corpora). Persists knowledge like "tireless colleague"—integrate via claude.md paths (e.g., executive agent reads /wiki/index/hot cache only if needed, avoiding always-on context bloat). Prompt Claude to build from high-level ideas ("Implement Karpathy's vague gist as my AI research brain"), customizing per use (YouTube vs personal).

Video description
Full courses + unlimited support: https://www.skool.com/ai-automation-society-plus/about?el=karpathy-obsidian All my FREE resources: https://www.skool.com/ai-automation-society/about?el=karpathy-obsidian Apply for my YT podcast: https://podcast.nateherk.com/apply Work with me: https://uppitai.com/ My Tools💻 14 day FREE n8n trial: https://n8n.partnerlinks.io/22crlu8afq5r Code NATEHERK to Self-Host Claude Code for 10% off (annual plan): https://www.hostinger.com/vps/claude-code-hosting Voice to text: https://ref.wisprflow.ai/nateherk Karpathy's idea gist: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f AI 2027 article: https://ai-2027.com/ Andrej Karpathy just shared his method for building LLM-powered knowledge bases using nothing but markdown files and Claude Code. In this video, I walk you through exactly how to set it up in about 5 minutes using Obsidian as a front end. I also show you two of my own wikis, one for YouTube transcripts and one for my personal second brain, and break down how this compares to traditional semantic search RAG. Sponsorship Inquiries: 📧 sponsorships@nateherk.com TIMESTAMPS 0:00 What We're Building 1:40 Karpathy's LLM Wiki Idea 3:12 Why It Matters & How It Works 5:39 Setting Up Obsidian & Claude Code 8:35 Ingesting Your First Article 13:02 Querying & Connecting Projects 15:36 LLM Wiki vs Traditional RAG 17:20 Final Thoughts

Summarized by x-ai/grok-4.1-fast via openrouter

8614 input / 1516 output tokens in 21378ms

© 2026 Edge