Obsidian is a second brain. I heard it for 10 years. I said it myself for 10 years. I was WRONG.
Any note-taking system is, at best, a second memory. More reliable in some ways. Useless in others. For a zettelkasten to actually work and pay off, the system alone isn’t enough. There have to be processes it’s wired into — every single day.
Usually those processes belonged to researchers and scientists. To people who write books. To people for whom Deep Work is a natural state. I turned Obsidian into a daily routine once — and believe me, it was hard, and it didn’t happen on the first try. And it still wasn’t a second brain. Until recently.
A brain isn’t memory. A brain is the set of processes tied to perceiving and handling information. A brain is wired to the peripheral nervous system. In a mammal’s brain, dozens of processes run in parallel that we never even notice. And yes, memory is an important part of the brain. But only a part.
You were probably waiting for me to bring up AI? Well. Here’s the moment.
My Obsidian became a real second brain when I let AI agents loose inside it. Claude Code first. Then Gemini. Then OpenClaw. Today my OpenClaw leans on the context we share on every single request. Here’s what I typically ask:
- find everything in Obsidian on this project
- find the latest draft of the blog post about X and add this idea to it…
- find the summary of the last AI Anti-FOMO meetup and make a YouTube thumbnail for the video
- run some research on this topic (the result always lands in Obsidian)
- pull the AI Sprint participant data and make a card in Obsidian for each one
But what about control? If Obsidian is my personal knowledge base — but an AI agent can write into it — is that knowledge still mine? Can you even call it knowledge?
Yes. With a caveat. Call it the Seneca caveat. A podcast summary an agent wrote is just a podcast summary. Research I ran through Parallel AI is not my research. A text I didn’t write is not my text. An agent can parse the internet forever, write its own texts, even learn from them. But it’ll be the one learning. Not me.
Then again — your own head is full of knowledge you never studied. You don’t know how, exactly, your brain runs your internal organs. You don’t know what it’s busy with while you sleep.
So it turns out there’s room in your head for all of it. Conscious and unconscious knowledge coexist just fine. Explicit and implicit processes. Maybe a couple of Billy Milligans in there too.
That’s my Obsidian now. There’s my knowledge and my texts (like this one), which the agent can only read. There’s shared knowledge — summaries of podcasts I listened to and read. There’s data from OpenClaw or Claude, which by now is read-only to me. That’s exactly what turned my knowledge base into a shared memory.
Second brain = me + my processes + shared memory + agents and their processes.