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

ArticleAgrici DanielTool

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.

Key points

  1. Built on Karpathy's LLM Wiki approach: Uses plain Markdown files rather than vector databases or external embedding services.
  2. Three plain core files: A hot cache holding around 500 words to prevent session amnesia, an index, and generated wiki pages.
  3. Automated ingestion: The tool analyses sources such as PDFs or URLs, drafts linked concept and entity notes, and flags contradictions.
  4. v1.9 'Compound Vault' update: Adds 15 skills (including /autoresearch and /think), hybrid retrieval (BM25 keyword search plus cosine reranking), and multi-writer advisory locking.
  5. Supports methodologies such as Zettelkasten, PARA, and LYT, maintaining full local-first access to all Markdown files.

Why it matters

Personal knowledge management systems frequently fail due to the ongoing friction of manual filing and cross-referencing. By integrating Claude Code directly with local Obsidian files, the vault remains durable and portable while automating linking and entity extraction.

Analysis

The project counters typical AI knowledge base architectures by rejecting heavy vector infrastructures in favour of plain text on disk. Treating raw Markdown as both memory and output ensures zero vendor lock-in, showing how agentic LLM tooling can maintain a dense knowledge graph without external database layers.

Mentioned links

Found in

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.

  • 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

  • Article:Wyndo

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

    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.

    AI & LLMs· Tutorial

  • 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

  • Repository:anthropics/knowledge-work-plugins

    Knowledge Work Plugins: Role-Specific Extensions for Claude Cowork

    Anthropic has open-sourced eleven plugins designed to tailor Claude Cowork and Claude Code to specific professional roles. Each plugin bundles skills, connectors, slash commands, and sub-agents for distinct knowledge work functions.

    23.9kstarsPython

    AI & LLMs· Tool

  • Repository:EveryInc/compound-engineering-plugin

    Compound Engineering: 33-Skill Plugin for AI Coding Agents

    Compound Engineering is an open-source plugin for AI coding agents designed to structure development workflows and systematically preserve learned context. It runs on 14 platforms, including Claude Code, Cursor, and Codex.

    24.9kstarsTypeScript

    AI & LLMs· Tool

  • Repository:anthropics/skills

    Anthropic Skills: Reference Repository and Specification for Claude Agent Skills

    Anthropic provides a public repository containing example skills, templates, and specifications for Claude's Agent Skills standard. Skills package instructions, scripts, and resources inside folders with a central SKILL.md file to enable repeatable workflows ranging from document generation to technical testing.

    174.3kstarsPython

    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.