Turns out, you can rewrite history. Well, a chatbot’s understanding of your personal history, anyway.

Customizing Claude’s Memory for a Personalized Experience

Since the summer of 2025, Claude has had the ability to remember past conversations. This feature, referred to as memory by Anthropic, allows the chatbot to personalize its responses and save users from having to repeat context. By default, memory is enabled for all Claude users, including those with free accounts. A recent update allows the chatbot to carry over its memory across both chats and Claude Cowork sessions. Anthropic has also introduced more granular controls, enabling users to edit specific topics that Claude remembers. Here’s how you can edit what Claude remembers about you.

How to Edit Claude’s Memory

Claude organizes its memory around specific topics. The easiest way to edit those topics is through the chatbot’s web client, accessible via claude.ai. Once there, follow these steps:

1. Select Settings from the profile page menu.
2. Click Memory.
3. Scroll down to find the Topics section.
4. Press the Edit icon to modify a memory, or the Delete icon to remove a topic from Claude’s memory.
5. If editing a memory, use the prompt bar to describe what Claude should change.

On mobile, follow these steps instead:

1. Tap the profile icon to access the Settings menu.
2. Under the App section, select Capabilities.
3. Scroll down and tap Memory files.
4. Select a topic.
5. If editing a memory, use the prompt bar to describe what Claude should change. Tap the trash icon to delete a memory instead.

Following Claude’s latest memory update, Anthropic added an option called Include sensitive topics in memory. By default, Claude won’t save memories related to subjects like health, race, ethnicity, religious beliefs, politics, or gender identity. Enabling this option allows Claude to record more sensitive information, with a notice appearing each time a memory related to a sensitive subject is generated. However, Claude will not retroactively save past conversations, and certain information, such as government ID numbers, will never be saved, even with this option enabled.

By default, Claude automatically generates memories for all users. This feature can be disabled by toggling off Generate memory from chats. Users can then choose to Pause memory or Reset memory, with the latter being irreversible. “Upon re-enabling the feature, you’ll start from scratch, and Claude will not have its previous memory,” Anthropic notes.

How Claude’s Memory Works in Projects

Anthropic has compartmentalized Claude’s memory in projects to prevent the chatbot’s context window from becoming overwhelmed with irrelevant information. Users can shape Claude’s memory in projects by adding comments, documents, and information from GitHub through the interface. At the end of each day, Claude generates a summary of the work completed, which can be edited from the same interface. If a user prompts Claude outside of a project, they can click or tap the three dots icon and select Add to project to properly sort the conversation. For information that should be remembered across all tools, users can add it to the Profile section of the Memory menu.

Additional Tips for Using Claude

If you want to temporarily prevent Claude from saving anything to its memory, you can switch to Incognito mode by clicking or tapping the ghost icon in the top right of the interface. “Incognito chats aren’t saved, added to memory, or used to train models,” Anthropic explains.

In March, Anthropic added an import tool to facilitate the transfer of conversations from other chatbots to Claude. Users can select Start import next to Import memory from other AI providers to initiate this process. For more detailed guidance, Engadget provides a full guide on how to export chats to Claude.