# I spent the past week building a personal knowledge base that the LLM manages...
Canonical: https://social-archive.org/nbluemer/C31ozTijhD
Original URL: https://www.linkedin.com/posts/yu-feng_i-spent-the-past-week-building-a-personal-share-7446641382351613952-EiGl/
Author: Louis W.
Platform: linkedin
## Content
I spent the past week building a personal knowledge base that the LLM manages for you — and I wanted to share what I learned. The insight came from Andrej Karpathy's post: most people use LLMs as smart search engines. But you can use them as librarians who own the library. Here's how it works: Feed it raw content: URLs, PDFs, images, notes - /kb-compile turns everything into a structured Obsidian wiki with tagged concept articles and backlinks - /kb-reflect runs automatically after every compile, reads the index, and writes synthesis articles connecting ideas across sources you never explicitly linked - /kb-ask navigates the wiki like a human expert (reads index first, picks 3-5 relevant articles, answers with citations) — no RAG, no embeddings infrastructure needed The part that surprised me most: the synthesis articles. Even with 10-15 sources, the reflection pass surfaced connections I hadn't made explicit and wrote them up as standalone articles. That's qualitatively different from search — search finds what you know is there. This surfaces what you didn't know you knew. The whole system ships as 9 Claude Code skills (plain markdown files) + a Python search CLI. One setup command. Works with existing Obsidian vaults. Wrote a full technical walkthrough on my blog: https://lnkd.in/gZ44zecd GitHub: https://lnkd.in/gfZETjJC