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 one 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 makes it into 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, searchable knowledge.”

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 any other note.

Queryable frontmatter

Stable YAML fields (source, title, dates, a link back) so a Dataview table can list every Claude chat about [[Project Atlas]], newest first.

Linkable title

[[that conversation]] autocompletes instead of forcing a timestamped filename.

Update in place

Re-running overwrites the existing file, matched by conversation id, not conversation (3).md.

Body fidelity

Code fences stay code, tables stay tables, math stays math.

No ceremony

No plugin, local REST server, or key. Your vault is already a folder.

Doing it with Carry

Carry is the browser extension we built for this inbound direction. Point it at the folder Obsidian already opens and it saves your conversations there as Markdown. It reads each provider through the session you already have, so code, tables, and LaTeX survive.

1. Install Carry and pick your vault folder.
2. Connect ChatGPT, Claude, and Grok.
3. Capture runs automatically for ChatGPT and Claude while Chrome is open. Grok is manual: run a capture with a signed-in grok.com tab open.

Each conversation becomes a note like this, under carry-backup/<provider>/:

---
conversation_id: "0d6c2c1e-…"
source: claude
type: conversation
title: "Planning the Atlas migration"
aliases:
  - "Planning the Atlas migration"
tags:
  - capture/claude
created: 2026-06-12T09:41:07
updated: "2026-06-12T10:02:55.120Z"
synced: 2026-06-12T10:05:00
url: "https://claude.ai/chat/0d6c2c1e-…"
message_count: 14
capture_version: 2
content_hash: sha256:9f2c…
---

**Human**

Compare the two migration paths for Atlas.

**Assistant**

Here's a table of both paths…

It closes the loop with direction one: the folder that makes a good Dataview citizen is also the folder your filesystem or Obsidian MCP server reads, so today’s conversations become part of the corpus you query tomorrow.

Common questions

Carry processes chats on your device and never uploads them. Verified compatibility settings download from carry.md, with an off switch. See privacy details.