# Step-by-Step Guide: Build Your Own AI Second Brain with Obsidian and Karpathy’s LLM Wiki Pattern
Canonical: https://social-archive.org/adegette/nP3EsIn3fG
Original URL: https://www.thetoolnerd.com/p/step-by-step-guide-build-your-own-second-brain-obsidian-kaparthy?r=bd8v9&utm_medium=ios&triedRedirect=true
Author: Akhil
Platform: web
## Content
### Build your AI Second Brain using Obsidian and Andrej Karpathy’s LLM Wiki pattern. Learn how to use agentic tools like Claude Code to turn raw notes into a persistent, self-organizing knowledge base ![Image](https://substackcdn.com/image/fetch/$s_!b62q!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fdc6f6513-6116-4d5f-8307-39d1d5edf932_1600x900.png) If you read this all the way through, you will end up with a working blueprint for a second brain that compounds over time. The goal is to replace scattered PDFs, browser tabs, notes, and chat threads with a system that keeps getting better as you add material. That is what makes Andrej Karpathy’s `llm-wiki` gist worth studying. GitHub shows the gist was first published on April 4, 2026.[1](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f#file-llm-wiki-md) The idea is simple and strong: instead of asking an LLM to rediscover your knowledge from raw files every time, you let it maintain a persistent wiki that keeps improving as new sources come in.[1](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f#file-llm-wiki-md) This guide turns that pattern into a practical setup for TheToolNerd readers. The stack is straightforward. > Use [Obsidian](https://tools.thetoolnerd.com/directory) as the local knowledge base, use an agentic coding assistant such as [Claude Code](https://www.thetoolnerd.com/p/i-tested-claude-code-for-a-week) to maintain the wiki, and use a simple ingest workflow so every useful article, note, or transcript has a home. If you already work with AI coding tools, this also fits well with my earlier write-ups on [Claude Code](https://www.thetoolnerd.com/p/i-tested-claude-code-for-a-week) and [Windsurf](https://www.thetoolnerd.com/p/windsurf-editor-by-codeium-wave-2). For adjacent tools, browse the [TheToolNerd directory](https://tools.thetoolnerd.com/directory). ## What you will get from this guide Before you start building, it helps to know what this setup is supposed to give you. ## Why this pattern matters Most people still use LLMs like temporary search layers. They upload documents, ask a question, get an answer, and move on. That works for one-off retrieval, but it does not build memory. Karpathy’s argument is different. He describes a persistent, LLM-maintained wiki that sits between you and your raw documents, so synthesis happens once and then gets updated over time instead of being recomputed from scratch on every question. > “The wiki is a persistent, compounding artifact. The cross-references are already there. The contradictions have already been flagged. The synthesis already reflects everything you’ve read.” - Andrej Karpathy That is the real shift. You stop treating the model like a temporary answer machine and start using it as a maintainer for a knowledge system.