@mylifcc: Recently while working on Agent memory and personal knowledge systems, I discovered this project obsidian-wiki, so fitting! It brings Andrej Karpathy's LLM Wiki pattern to Obsidian: enabling AI Agents to autonomously inges…
Summary
This tweet introduces the obsidian-wiki project, which implements Andrej Karpathy's LLM Wiki pattern on Obsidian, allowing AI Agents to autonomously ingest multi-source knowledge and organize it into a wikilink-interconnected markdown knowledge base. It supports Delta incremental updates and source attribution (provenance), and has built-in features like query, audit, graph export, etc. Currently at 2k stars.
View Cached Full Text
Cached at: 06/15/26, 11:09 PM
Recently, while working on Agent memory and personal knowledge systems, I came across this project—obsidian-wiki—and it’s exactly what I needed!
It brings Andrej Karpathy’s LLM Wiki mode to Obsidian:
Enabling AI Agents to autonomously ingest multi-source knowledge (PDFs, chat logs, images, etc.), automatically organize it into a wikilink-interconnected markdown knowledge base, and continuously maintain, query, and evolve it.
Key highlights: Delta incremental updates + source attribution (provenance), greatly reducing knowledge staleness and hallucinations
Built-in skills: query, audit, graph export, GitHub sync, daily-update
Can be directly symlinked into workflows like Claude Code, Cursor, etc.
Latest version supports OKF import/export
Currently at 2k stars and actively updated today. This is essentially an independent developer turning the idea of an “Agent-driven second brain” into practical, deployable infrastructure.
Similar Articles
@rwayne: https://x.com/rwayne/status/2054523563248611675
This article details how to build a fully automated local knowledge base system using Hermes Agent, Obsidian, and LLM Wiki, enabling automatic note organization, bidirectional linking, and persistent accumulation.
@Huanusa: The ceiling of personal knowledge bases has arrived! This GitHub LLM Wiki project has already garnered 2800+ Stars, completely leaving ordinary RAG in the dust! It's not the useless mode of "re-retrieving" every time, but lets AI directly help you incrementally build a truly structured Wiki — compile knowledge once, and it continuously evolves...
LLM Wiki is an open-source desktop application that uses LLM to incrementally build a structured knowledge base, supporting knowledge graphs, community detection, Obsidian integration, and Chrome clipping, aiming to replace traditional RAG approaches.
@yunxi0623: https://x.com/yunxi0623/status/2068171252595147166
Introduces how to use Obsidian and Claude Code to build a local AI knowledge base, by creating folder structures, writing CLAUDE.md rule files, and step-by-step importing and organizing materials, to achieve long-term portable personal knowledge management.
@coldsake_: https://x.com/coldsake_/status/2067374833692815638
This article introduces how to use Obsidian combined with AI tools like Codex/CC to build an academic literature management system, enabling automatic classification, duplicate checking, generation of wiki pages and an academic toolbox, and shares methods for reading literature and improving academic skills.
@ziwenxu_: https://x.com/ziwenxu_/status/2053241837453029439
The article details a workflow for creating an automated 'Codex Knowledge Vault' using Obsidian, where AI agents automatically ingest and organize daily bookmarks into a structured knowledge base to reduce context debt.