Guides
Explain less. Get more done.
How to give your assistants a memory you own – step by step, without the jargon.
Obsidian & Claude
How to connect your Obsidian vault to Claude, ChatGPT and Cursor via MCP, locally or in the cloud.
ReadRun your company with AI
How I run several ventures from one vault that Claude, Claude Code and ChatGPT all read.
ReadLLM Wiki
Karpathy’s idea explained: an AI maintains your knowledge as a Markdown wiki. With a template to copy and a hosted setup, no scripts.
ReadClaude memory
Built-in memory, Projects or a shared vault over MCP: an honest comparison, and when each one is enough.
ReadClaude connectors
What connectors in Claude are, how to add a custom one with an MCP URL, and which ones are actually worth it.
ReadClaude Code memory
CLAUDE.md or a memory over MCP? A rule of thumb for what goes where, and the setup in one command.
ReadChatGPT memory
What ChatGPT remembers, where that stops, and how to share one memory with Claude and Cursor over MCP.
ReadMCP memory server
What a memory server for Claude, ChatGPT and Cursor does, local vs hosted, and what to look for before you pick one.
ReadDecision log
A template for decisions you’ll still understand six months from now – with a filled-in example to copy.
ReadWhat is MCP?
The Model Context Protocol in plain English, and how to connect an MCP server to Claude or ChatGPT.
ReadAI & GDPR
Using Claude and ChatGPT with your data: the two places that matter, and a checklist.
ReadAI second brain
A second brain your AI agents help write: three approaches compared, a structure to copy and four everyday workflows.
ReadBasic Memory vs WhyVault
Two Markdown memories for your AI agents, compared honestly: when Basic Memory fits better, and when WhyVault does.
Read
Try it with your own vault.
Set up in two minutes, free up to 20 notes, no credit card.