Claude, the chatbot developed by Anthropic, has been able to remember past conversations since the summer of 2025. This feature, known as memory, allows the chatbot to personalize its responses and save users the hassle of repeating context. Recently, Anthropic has rolled out more granular controls, giving users the ability to edit the specific topics Claude remembers.
To edit Claude's memory, users can follow these steps on the web client: select Settings from the profile page menu, click Memory, scroll down to the Topics section, and press the Edit icon to modify a memory or the Delete icon to remove a topic. On mobile, users can tap the profile icon, select Capabilities, scroll down to Memory files, select a topic, and use the prompt bar to describe what Claude should change or tap the trash icon to delete a memory.
Anthropic has also added an option called Include sensitive topics in memory, which allows Claude to record more sensitive information. However, this feature is disabled by default, and users must enable it to allow Claude to save memories related to subjects like health, race, ethnicity, religious beliefs, politics, or gender identity. Each time Claude generates a memory related to a sensitive subject, users will see a notice.
Claude's memory can be siloed 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. At the end of each day, Claude will generate a summary of the work it's done, which users can edit from the same interface.
If users want to temporarily avoid the possibility of Claude writing something to its memory, they can switch the chatbot to Incognito mode. Anthropic has also added an import tool to make it easier for users to bring their conversations from other chatbots over to Claude.
Este artigo foi escrito com a assistência de IA.
News Factory APP - notícias agênticas para impulsionar seu SEO e AEO.