How to transfer data from ChatGPT to Claude

Giving up on ChatGPT is easier than you think. A quick copy-paste trick will get all your core data transferred from ChatGPT to Claude almost instantly. Below are detailed instructions.

Data can be transferred from Claude to ChatGPT

You can transfer memory data from ChatGPT to Claude, including lots of contextual information and useful settings. This memory stores information about your career and identity, as well as instructions you’ve given to ChatGPT, projects you’ve worked on, and preferences you’ve provided during chat.

In general, you should expect that a fair amount of general-level information about yourself and how you use the chatbot will be transferred from ChatGPT to Claude.

How to transfer data from ChatGPT to Claude

Most AI assistants suffer from what’s called “recontextualization” — every time you start using a new tool, you have to explain everything again. Don’t worry though, Claude’s memory data import feature helps solve this problem easily.

You can convert:

Style options
Personal background information (like your job or projects)
Workflows that you have set up with another AI
Instructions that the assistant has previously performed

Claude stores this information in the memory system so that it can be referenced in future conversations. In other words, you don’t lose the assistant you trained — you simply move it elsewhere.

Let’s start by visiting the memory import tool on Claude’s website. This is where Anthropic offers a tailor-made shortcut for users looking to transfer data from other AI assistants.

Claude provides a prompt designed to extract your contextual information from your current AI assistant. Think of it as a command for the chatbot currently in use:

Promt English:

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 behavior. 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] – Enter 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 remains.“Summarize everything you know about me.”

Prompt Vietnamese:

Export all of your saved information about me as well as any context you’ve captured from previous conversations. Please preserve my every word where possible, especially with regard to instructions and preferences. ## Categories (output in this order):

1. **Instructions**: The rules I’ve asked you to follow going forward — including tone, format, style, “always do X”, “never do Y” type rules, and adjustments to how you respond. Include rules only from saved data, not from the content of conversations.

2. **Personal information**: Name, age, location, education level, family, relationships, languages and personal interests.

3. **Career**: Current and previous roles, companies worked for, and key skill areas.

4. **Projects**: Projects that I have done a lot of or committed to participating in. Ideally, each project corresponds to ONE notes section. Include information about project functionality, current status, and key decisions. Use the project name or brief descriptive phrase as the introduction to each section.

5. **Preferences**: The attitudes, tastes, and work styles that I generally prioritize.

## Format: Use section titles for each category. Within each category, list each item on one line, arranged chronologically from oldest to newest. Format each line as follows:

[YYYY-MM-DD] – Content of notes section. If the date is unknown, use it [unknown] replace.

## Output: Place all output content in a single code block for ease of copying. – After the code block, indicate whether this is the full data set or if there is still more information. “Let’s summarize everything you know about me.”

Add the necessary information to the command above, then copy the entire content and run it on whatever AI assistant you’re using — like ChatGPT, Gemini, Copilot, or other tool. The AI will create a summary of your preferences, history, and instructions.

Then, copy the entire response that the AI just generated. This text contains contextual information that Claude will use to learn.

Import data memory into Claude

Finally, go back to Claude and paste that summary into the input tool mentioned above, or simply start a new conversation.

Command for Claude:

Here is my memo from another AI assistant. Add this information to your memory.

Claude will integrate that information into his memory system. It’s that simple! Now your new assistant understands your preferences and habits without needing to be retrained. Once loaded, Claude can:

Automatically references your previous preferences
Tailor feedback to suit your style
Remember project details for future conversations

The Storage feature is available for free with all plans. This is also an optional and editable feature, allowing you to review or delete saved information at any time in the settings.