# # 156 Build Karpathy's Second Brain With Obsidian + Claude Code

Page: https://stenobird.com/podcast/build-with-ai-6407453/156-build-karpathy-s-second-brain-with-obsidian-claude-code
Text version: https://stenobird.com/podcast/build-with-ai-6407453/156-build-karpathy-s-second-brain-with-obsidian-claude-code.md
Podcast: [Build With AI](https://stenobird.com/podcast/build-with-ai-6407453)
Published: 2026-04-07T16:07:41+00:00
Episode link: https://share.transistor.fm/s/d0fe7c2a
Audio file: https://media.transistor.fm/d0fe7c2a/8a59a7e1.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/build-with-ai-6407453/episodes/156-build-karpathy-s-second-brain-with-obsidian-claude-code
Duration seconds: 1341

## Resource

Download Nick's free second brain skill -- one-click install that sets up your entire Obsidian vault and ingestion workflow inside Claude Code: https://return-my-time.kit.com/286e11f7e6I brought on Nick Spisak to build a complete second brain live -- start to finish, in under 20 minutes. By the end of this episode, you'll know exactly how to build your own second brain -- and you can grab Nick's free skill to do it in one click.Timestamps00:00 - Intro and Karpathy's viral second brain tweet00:24 - What the second brain concept is03:28 - Obsidian Web Clipper: scraping pages into your vault04:41 - Nick's free skill: wizard, ingest, query, and lint commands05:53 - Live demo: running the setup wizard in Claude Code08:38 - How many vaults to manage: personal vs. business10:30 - Opening the vault and exploring the file structure12:21 - Graph view: seeing connections between your data15:38 - Ingest command: raw data into organized wiki16:29 - Automating ingestion on a cron schedule19:12 - Compounding value and syncing the vault across devices20:19 - Pruning the vault with the lint command21:53 - Your data set as a moat in the AI ageKey Points* Karpathy released a framework for building an LLM knowledge base. Nick turned it into a free Claude skill with a guided setup wizard, ingest, query, and lint commands -- works across Claude Code, Codex, Gemini CLI, and more. One-click install, no coding required.* The system runs on three tiers: raw (brain dump), wiki (AI-organized knowledge base), and outputs (answers from querying). Drop files into raw, run ingest, and the AI maps everything into structured wiki entries with relationship graphs.* You can automate ingestion using Claude Code's loop feature so the vault stays current without manual work. Pair with Obsidian's paid sync t…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/build-with-ai-6407453/episodes/156-build-karpathy-s-second-brain-with-obsidian-claude-code/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/build-with-ai-6407453/156-build-karpathy-s-second-brain-with-obsidian-claude-code.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.