Import your ChatGPT memory into Claude

The months you spent correcting ChatGPT come back with you, so Claude starts already knowing your job, your style and your regulars instead of guessing at them. Nothing gets copied out by hand. The whole move rides on one prompt, and Claude is the one that wrote it, so you can read exactly what you are handing over before you send it. It is printed in full below.

To import your ChatGPT memory into Claude, open Claude's Memory settings and start an import from another provider. Claude gives you a prompt. Paste that prompt into ChatGPT, copy the memory export it produces, then paste that back into Claude.

How to carry it across

1. Start the import in Claude. Open Claude's Settings, then Memory, then Import memory from other AI providers, and press Start import. Claude hands you a prompt to run in ChatGPT. It is the same prompt shown below, so you know exactly what you are asking for.
2. Copy the prompt. Grab the prompt from the copy block below. It is written to make ChatGPT list everything it has saved about you in clean, dated categories, wrapped in one code block you can copy in a single tap.
3. Paste it into ChatGPT and send. Open ChatGPT, paste the prompt, and send it. ChatGPT writes out your instructions, identity, career, projects and preferences as one tidy block, and tells you if there is more to pull.
4. Paste ChatGPT's output back into Claude. Copy the whole block ChatGPT produced and paste it back into the Claude import, or into a chat where you say "remember this about me". Claude now starts every chat knowing what ChatGPT knew.
5. Read it before you paste, and cut the sensitive bits. The export can hold things you have forgotten you said. Skim it and drop anything private or no longer true, so you carry across the useful context and nothing else.

The prompt Claude gives you

This is the exact prompt. Copy it, paste it into ChatGPT, and it returns everything ChatGPT knows about you in one code block, ready to paste back into Claude.

Export all of my stored memories and any context you've learned about me from past conversations. Preserve my words verbatim where possible, especially for instructions and preferences.

## Categories (output in this order):

1. **Instructions**: Rules I've explicitly asked you to follow going forward, tone, format, style, "always do X", "never do Y", and corrections to your behaviour. Only include rules from stored memories, not from conversations.

2. **Identity**: Name, age, location, education, family, relationships, languages, and personal interests.

3. **Career**: Current and past roles, companies, and general skill areas.

4. **Projects**: Projects I meaningfully built or committed to. Ideally ONE entry per project. Include what it does, current status, and any key decisions. Use the project name or a short descriptor as the first words of the entry.

5. **Preferences**: Opinions, tastes, and working-style preferences that apply broadly.

## Format:

Use section headers for each category. Within each category, list one entry per line, sorted by oldest date first. Format each line as:

[YYYY-MM-DD] - Entry content here.

If no date is known, use [unknown] instead.

## Output:

- Wrap the entire export in a single code block for easy copying.
- After the code block, state whether this is the complete set or if more remain.

Where the line is

Do it now, in five minutes

Open Claude's Memory settings and start the import, copy the prompt, run it in ChatGPT, then paste the block it returns back into Claude. Start a fresh Claude chat and ask what it knows about you. If it plays your context back, you have moved across without losing a thing.

Want to understand the place you are saving it to first? Read how to make Claude remember you without retyping.