What is Karpathy's LLM Wiki?

A pattern where an LLM agent maintains a persistent markdown wiki of knowledge, instead of RAG-rederiving everything per query. Obsidian + Claude Code does the heavy lifting.

How does Hjarni improve on local LLM Wiki?

Hosts it cloud-side via MCP, so any LLM (Claude, ChatGPT, Cursor) accesses from anywhere—no machine limits, no sync, shared brains for teams.

Is Hjarni better than Obsidian for AI knowledge management?

If you want cross-LLM, everywhere access—yes. Trade git/filesystem/plugins for zero-friction ubiquity. Obsidian shines for local purists.

🤝 Community & Governance

Karpathy's LLM Wiki Goes Cloud-Native: Hjarni Fixes the Friction That Killed It for Me

Everyone thought we'd just RAG-bomb LLMs with docs forever. Karpathy's wiki flips the script, and Hjarni turbocharges it into a shared, frictionless brain.

theAIcatchup Apr 09, 2026 3 min read

Digital brain network linking LLM clients like Claude, ChatGPT, and Cursor to a central hosted wiki

⚡ Key Takeaways

Karpathy's LLM Wiki beats RAG by maintaining persistent, compounded knowledge via LLM agents. 𝕏
Local setups suffer from device, client, and sharing friction—Hjarni fixes it with hosted MCP access. 𝕏
This realizes Vannevar Bush's Memex vision, paving for shared 'team brains' in AI workflows. 𝕏

Published by

theAIcatchup

Community-driven. Code-first.

#Andrej Karpathy #Hjarni #LLM Wiki #RAG alternative #knowledge management

Worth sharing?

Get the best Open Source stories of the week in your inbox — no noise, no spam.

Originally reported by Dev.to

⚡ Key Takeaways

The 60-Second TL;DR

theAIcatchup

Share this article

Worth sharing?

Related Stories

Claude Code's Upstream Proxy: The Stealthy Traffic Cop Revolutionizing AI Dev Containers

Anthropic's Claude Mythos: The AI Exploit Machine Locked Away from You

Three Layers That Make Claude API Agents Survive Production Hell

Meta's Muse Spark: 16 Tools Buried in a Chatbot That Actually Work

Stay in the loop