Making your Obsidian vault work with AI (it already does — here's the part that doesn't)

Your vault already works with AI, for the least glamorous reason there is: it’s a folder of plain Markdown. As the top comment on the Show HN thread for OpenKnowledge (an AI-first Obsidian alternative) put it:

“I don’t understand how Obsidian, a collection of markdown files, isn’t already AI friendly. It’s hard for me to imagine a more AI-friendly but still usable way to organize your notes.” — culi

So the question splits into two directions. One is mostly solved. The other is the actual gap.

Direction one: AI reading your vault (mostly solved)

Markdown is the most machine-readable, future-proof, model-agnostic format a knowledge base could be in — no proprietary schema, no database, no export step. A language model, or a person with grep, reads it directly. So “let an AI read my vault” is already answered; you don’t need to build anything. From lightest to heaviest:

• Point a coding agent at the folder. Open the vault in your editor and let Copilot or Claude Code work over the .md files. For a lot of people that’s the whole solution.
• Wire it up over MCP. For Claude to search and traverse your vault as a first-class thing, the servers exist: mcp-obsidian, obsidian-mcp-server, or the official filesystem MCP with no plugin at all. “Use Obsidian as Claude’s memory” is a documented pattern, not a research project.
• In-vault plugins, if you want retrieval to live inside Obsidian itself, are a mature category too.

Pick the lightest option that fits and move on. The interesting problem is the other direction.

Direction two: your AI thinking reaching the vault (the actual gap)

Your vault can be read by any AI you like. But a growing share of your actual thinking now happens inside the AI — the messy first drafts, the explanation that finally clicked, the plan you talked your way into — and none of it lands in the vault. It sits in a chat history behind a login, on a server you don’t control, in a format you can’t query. Your second brain has a hole in it, shaped exactly like the conversations you had this week.

This is a real, repeated ask. Someone filed it as a feature request against an unrelated tool: developers “want to pipe notable AI sessions into their second brain… turning AI conversations into permanent notes.”

So the useful question isn’t “which AI app should replace my vault.” It’s: what would it take to get my AI conversations into the vault I already have — as good citizens, not as junk?

What good inbound capture looks like

Dumping a transcript into your vault as a wall of text isn’t capture; it’s litter. A conversation earns its place only if the vault’s own machinery — Dataview, the graph, tag search — can act on it like anything else. That means:

• Frontmatter you can query. Stable, consistently-named YAML fields — source, title, dates, a link back — so a Dataview table can pull “every Claude chat about [[Project Atlas]], newest first” without cleanup.
• A wikilink-able title. Clean enough that [[that conversation]] autocompletes instead of forcing you to type a timestamped filename.
• Update in place, not duplicate. Re-running the capture overwrites the existing file, matched by conversation id — not conversation (3).md. The loudest complaint about copy-paste-and-scripts is “ran it twice, got 200 duplicates.”
• Body fidelity. Code fences stay code fences, tables stay tables, math stays math.
• No plugin, no API key, no self-signed certificate. The heavier integrations ask you to install a plugin, run a local REST server, and paste in a key — a lot of ceremony for “save my chats,” and why most people never finish. Your vault is already just a folder; anything that writes good Markdown to it is “Obsidian support.”

Doing it with Carry

Carry is a browser extension built for this inbound direction — the capture layer for your AI conversations, not another exporter or an app that replaces your vault.

You point it at the folder Obsidian already opens, connect the provider you’re logged into (no API key, no developer account — it uses the session you already have), and sync from the popup. Carry pulls your recent conversations — around the last 20 per provider — and writes each as a Markdown file with frontmatter you can query later:

---
conversation_id: "abc123"
source: claude
title: "Explain CRDTs like I'm five"
created: "2026-06-15T10:23:00.000Z"
updated: "2026-06-15T10:40:00.000Z"
synced: "2026-07-08T10:00:00.000Z"
url: "https://claude.ai/chat/abc123"
---

**Human**

Explain CRDTs like I'm five.

**Assistant**

Imagine two kids drawing on the same whiteboard...

Because it reads the provider’s own history rather than scraping the rendered page, code, tables, and LaTeX come through intact. Because each file is matched by its conversation id, re-syncing overwrites in place — run it as often as you like and never end up with duplicates, even if you’ve renamed the file.

Sync is manual today: open the popup and run it. Automatic capture is on the way but doesn’t ship yet, so I won’t pretend it does. What ships now is a two-minute setup that turns “I meant to save that chat” into a folder of real Markdown files.

And it closes the loop with direction one: the same clean folder that makes a good Dataview citizen is the folder your filesystem or Obsidian MCP server reads. The conversations you capture today become part of the corpus Claude Code queries tomorrow — both directions pointing at the same pile of Markdown. Your vault was always AI-friendly; the point was never to make it smarter, but to stop leaving half your thinking outside it.

Carry is local-only — no server, no account, and only the providers you connect. It syncs Claude, ChatGPT, and Grok into your own folder as Markdown — see how it works to get started.