LLM Knowledge Base Systems
The Hermes Agent now includes Karpathy's LLM-Wiki for creating knowledge bases and research vaults with Obsidian. LLM-Wiki is a method for building personal knowledge bases using LLMs, allowing for a persistent, compounding knowledge base that doesn't require retrieving information from scratch every time. This approach replaces traditional RAG systems, enabling LLMs to build and maintain a structured, interlinked collection of markdown files. The integration with Hermes Agent and Obsidian facilitates the creation of a living wiki that keeps getting smarter.
Engagement Score Over Time
Top Posts
Hermes Agent now comes packaged with Karpathy's LLM-Wiki for creating knowledgebases and research vaults with Obsidian!
In just a short bit of time Hermes created a large body of research work from studying the web, code, and our papers to create this knowledge base around all
Andrej Karpathy thinks RAG is broken. He published the replacement 2 days ago. 5,000 stars in 48 hours.
It's called LLM Wiki.
A pattern where your AI doesn't retrieve information from scratch every time. It builds and maintains a persistent, compounding knowledge base.
The LLM Wiki by @karpathy is now a built-in skill in Hermes-Agent, give it a try
Karpathy's Second Brain idea just killed RAG.
LLMs can now turn papers, repos, and notes into a living wiki that keeps getting smarter.
And people are already doing wild use cases with it.
10 examples:
after Karpathy shared his Obsidian-based LLM wiki it got insta-viral
as it works better than 99.9% of AI memory systems...
these Obsidian skills will help your agents a ton with understanding Obsidian really well,
open source repo has over 20k Stars:
https:// github.com/kepano/obsidia n-skills …
