How I built a second brain with Claude and Obsidian

For years my notes were scattered across apps that didn’t talk to each other. Then I rebuilt everything around one idea: store knowledge as plain text, in folders, so an AI can read it, write to it, and reason over it. That’s the whole trick. Here is the exact setup, why each piece is there, and what I’d change if I started today.

The principle: plain text wins

Everything lives as Markdown files in a single folder (a “vault”). No proprietary database, no lock-in. Plain text is the most durable format there is, and, crucially, it’s the format AI models are best at. If your notes are plain text in folders, any capable model can navigate them like a codebase.

That single decision is what makes the rest possible.

The stack

• Obsidian: a free, local-first Markdown editor. It’s just a nice window onto a folder of .md files. Use it for linking notes, search, and graph view.
• Claude Code: an agent that runs in your terminal with read/write access to that same folder. This is the brain that reads and writes your notes.
• Git (optional but recommended): version history and backup. Your second brain is too valuable to live on one disk.

That’s it. No servers, no subscriptions beyond the AI itself.

Structure: PARA, lightly

I organise the vault with PARA, four top-level folders:

• Projects: things with a deadline or an outcome.
• Areas: ongoing responsibilities (work, health, finances).
• Resources: reference material I’ll reuse.
• Archive: done or dormant.

PARA is popular for a reason: it’s shallow, it’s obvious, and an AI can predict where something belongs. Don’t over-engineer the hierarchy. Depth is the enemy. If you’re nesting five folders deep, you’ve lost.

The one file that makes it work: the index

The single highest-leverage thing I added is a VAULT_INDEX.md at the root: a one-line summary of every note, grouped by folder. When I start a session, the AI reads the index first. It’s a map, enough to know which notes are relevant, so it can then open only those.

This matters for two reasons:

1. Token cost. Reading a 60-note index is cheap. Reading 60 full notes is not.
2. Accuracy. A model with a good map makes far better decisions about what to read than one that’s guessing.

The rule I follow: the index is a pointer, never the content. The AI always opens the actual note before answering. The index just tells it where to look.

Two commands do all the work

I wrapped the workflow in two reusable commands (in Claude Code these are saved “skills” or slash-commands):

load: orient the AI

Reads the index, confirms what’s in the vault, and announces it’s ready. I run this at the start of any session where I’ll ask questions about my own knowledge. Thirty seconds, and the assistant knows the shape of everything I know.

import: file new content

This is the workhorse. I paste in a transcript, an article, a voice-note dump, or a meeting summary, and the command:

1. Decides which PARA folder it belongs to.
2. Distils it (I have different modes, from full capture to a tight summary).
3. Writes it as a clean note with consistent frontmatter (tags, status, source).
4. Updates the index so the new note is discoverable next time.

The discipline of always updating the index on write is what keeps the system from rotting.

What it’s actually good for

• Recall across time. “What did I conclude about X last year?” gets answered from my own notes, not a generic web answer.
• Connecting ideas. The AI spots links between a book note and a work problem that I’d never have joined manually.
• Drafting from my own material. This very article was drafted from my notes about building the system. The brain writes about itself.

What I’d do differently

• Start the index on day one. I added it late and had to backfill. Don’t.
• Keep frontmatter boring and consistent. A fixed set of fields (tags, status, source, date) beats creative metadata every time. Consistency is what the AI relies on.
• Resist folder depth. Every time I went deeper than two levels, I regretted it.
• Version it from the start. Put the vault in Git early. Future-you will want the history.

The honest caveat

A second brain is a tool, not a personality transplant. It won’t think for you. It makes the thinking you already do compound. The value shows up over months, as the notes accumulate and the connections get richer. The first week feels like overhead. The first year feels like a superpower.

---

This is the first of a series on building with AI around a full-time job. Next: turning this same idea into a personal assistant that handles tasks, calendar, and relationships. A clean, anonymised starter version will be linked here once it’s ready.