LLM Wiki: Building an AI-Powered Second Brain in Obsidian

ArticleWyndoTutorial

Inspired by an idea from Andrej Karpathy, author Wyndo outlines a workflow using Claude Code and Obsidian Skills to automatically compile, cross-link, and maintain a personal knowledge base.

Key points

  1. Based on Andrej Karpathy's framing: Obsidian acts as the IDE, the LLM functions as the programmer, and the wiki serves as the codebase.
  2. Addresses the heavy maintenance burden of systems like Zettelkasten by having an LLM compile sources and handle cross-referencing automatically.
  3. Three-layer architecture: immutable source inputs (sources/inbox), LLM-compiled knowledge pages (wiki), and operational governance via CLAUDE.md.
  4. Integrates Obsidian Skills (released by Obsidian CEO Steph Ango) to teach Claude native syntax such as wikilinks, callouts, canvases, and the CLI.
  5. Driven by slash commands including /ingest-url (compiles sources across multiple pages), /process-inbox (classifies notes), and /lint-wiki (checks for broken links and gaps).

Why it matters

Personal knowledge management often fails due to the manual overhead of linking and tagging. Shifting maintenance to an agentic LLM workflow allows users to aggregate diverse inputs into an interconnected knowledge graph without constant manual bookkeeping.

Analysis

This method inverts typical knowledge retrieval: rather than maintaining notes by hand and querying an LLM ad hoc, the model handles synthesis and structuring behind the scenes. Operating directly on local Markdown files preserves data ownership while using terminal-driven agents to automate knowledge compilation.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Agrici Daniel

    claude-obsidian: Self-Organising Knowledge Base with Claude Code

    Agrici Daniel introduces claude-obsidian, a free open-source plugin for Claude Code. It implements Andrej Karpathy's LLM Wiki pattern to automatically compile and link Obsidian vaults from raw documents without requiring a vector database.

    AI & LLMs· Tool

  • Repository:AgriciDaniel/claude-obsidian

    claude-obsidian: Local-First AI Knowledge Management for Obsidian and Claude Code

    claude-obsidian is an MIT-licensed open-source project that connects Claude Code with Obsidian into a self-organizing knowledge graph. Implementing Karpathy's LLM Wiki pattern, it maintains a structured vault made entirely of local plain Markdown files.

    14.6kstarsPython

    AI & LLMs· Tool

  • Repository:kepano/obsidian-skills

    obsidian-skills: Agent Skills for Obsidian and Open Formats

    The open-source repository kepano/obsidian-skills equips AI coding agents with capabilities to interact with Obsidian vaults. Built on the Agent Skills specification, it works with agents like Claude Code, Codex, and OpenCode.

    47.9kstars

    AI & LLMs· Tool

  • Link:portablellm.wiki

    Portable LLM Wiki: Portable Personal Context for LLMs via URL and MCP

    Portable LLM Wiki is a tool that turns bios, resumes, and personal notes into a structured wiki. It exposes this context to LLMs like ChatGPT, Claude, and tools like Cursor through a simple URL, a QR code, or the Model Context Protocol (MCP).

    AI & LLMs· Tool

  • Link:Emmimal P Alexander

    Local Markdown Compiler Replaces LLM Wikis Using Pure Python

    Emmimal P Alexander replaced an agentic LLM-based personal wiki with a pure Python compiler. The tool processes raw text notes into a linked markdown wiki deterministically, without API calls, embeddings, or third-party dependencies.

    AI & LLMs· Tool

  • Link:agentwikis.com

    Agent Wikis: Maintained Knowledge Bases for Humans and AI Agents

    Agent Wikis transforms fast-moving information sources such as repositories, changelogs, transcripts, and community Q&A into structured Markdown knowledge bases. Designed for both humans and AI agents, the content is accessible via an llms.txt entry point.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.