ChatGPT to Obsidian: Complete Workflow for Exporting AI Conversations as Markdown Notes

If you live in Obsidian, every valuable ChatGPT conversation deserves a permanent home in your vault. Here’s the frictionless workflow that makes it happen.

The end state

Every ChatGPT conversation worth preserving becomes:

• A .md file in ~/vault/AI/ChatGPT/ (or your preferred location).
• Filename format: 2026-05-09 - rust async pitfalls.md.
• YAML front matter with title, model, date, platform, and tags.
• Properly nested headings, code fences with syntax highlighting, math delimiters intact.
• Connected to your existing notes through Obsidian backlinks.
• Fully searchable via Obsidian’s powerful full-text search.

The tools

• Obsidian, your knowledge vault.
• ChatExport AI, Chrome extension that exports ChatGPT conversations to pristine CommonMark Markdown.
• Three optional Obsidian plugins (first one is essential):
  • Templater, automates file naming and front-matter generation.
  • Dataview, query AI notes by tag, model, or date.
  • Smart Connections, semantic search across your AI conversation archive.

Step-by-step

Step 1: Export the conversation as Markdown

Open your ChatGPT conversation. Click the ChatExport AI toolbar icon to launch the export sidebar.

Select Markdown (.md). Enable Front matter to include YAML metadata at the top.

Click Export. Your .md file downloads instantly.

Step 2: Drop into your vault

Move the file to ~/vault/AI/ChatGPT/ or whatever folder structure fits your system.

The default filename looks like chatgpt-2026-05-09-12-34-56.md. Rename it to something descriptive like 2026-05-09 - rust async pitfalls.md. Templater can handle this automatically.

Step 3: The front matter ChatExport AI adds

---
title: "Rust async pitfalls — Tokio runtime questions"
platform: ChatGPT
model: GPT-5
exported: 2026-05-09T12:34:56Z
url: https://chatgpt.com/c/abc123...
tags: [ai, chatgpt, rust]
---

The tags field starts with [ai, chatgpt]. Add your own custom tags (rust, async, tokio) so Dataview can surface related notes later.

Step 4: Review and prune

Long ChatGPT threads often contain dead-ends and tangents. Open the note in Obsidian, trim the noise, and keep the signal.

Better yet, do this before exporting, ChatExport AI includes per-message checkboxes so you can choose exactly which exchanges to include. This “trim before export” approach eliminates editing work in Obsidian.

Step 5: Link to other notes

Use Obsidian’s [[wikilink]] syntax to weave the AI note into your knowledge graph:

This came up while working on [[Project Helios]] — see also
[[Tokio runtime variants]] and the original
[[2026-05-08 ChatGPT - tokio task::spawn_blocking notes]].

After a few weeks, your AI notes transform from isolated conversations into a richly connected knowledge network.

Power moves

Auto-rename via Templater

Templater script that automatically renames files based on YAML front matter:

<%* 
const file = tp.file.find_tfile(tp.file.path(true));
const meta = app.metadataCache.getFileCache(file)?.frontmatter;
if (meta?.title && meta?.exported) {
  const date = meta.exported.slice(0, 10);
  const slug = meta.title
    .toLowerCase()
    .replace(/[^a-z0-9]+/g, '-')
    .replace(/^-|-$/g, '')
    .slice(0, 60);
  await tp.file.rename(`${date} - ${slug}`);
}
%>

Query AI notes via Dataview

TABLE platform, model, exported
FROM "AI"
WHERE platform != null
SORT exported DESC
LIMIT 25

This creates a dashboard showing your last 25 AI conversations, sorted by date and filterable by platform.

Semantic search across AI notes

Smart Connections creates embeddings of your notes and enables semantic search. Perfect for when you remember the concept but not the exact title.

What about Claude, Gemini, and other AI platforms?

Identical workflow. ChatExport AI exports Claude, Gemini, Perplexity, and 45+ other AI platforms to Markdown. The YAML platform field identifies which AI generated each conversation.

Why this workflow is worth the setup

The first month is an investment. By month three, you’ll have a personal AI knowledge base, every research thread, debugging session, and brainstorm, searchable, interconnected, and completely under your control. Conversations don’t vanish when ChatGPT free-tier history expires. The insights live permanently in your vault.

Related

• How to export ChatGPT to Markdown, detailed export guide.
• For writers, Obsidian-first writing workflows.
• For researchers, citation-heavy research archives.