Anthropic today announced that the recent memory feature in Claude is being rolled out to Pro and Max plan users, making it available to all paid users now.
Memory was initially announced in early September, but was only available to Team and Enterprise users to begin with.
Memory allows Claude to remember your projects and preferences so that you don’t need to re-explain important context across sessions. “Great work builds over time. With memory, each conversation with Claude improves the next,” Anthropic wrote in its initial announcement.
Each project can have its own separate memory to keep boundaries between different conversations, such as product launch planning not mixing with client work, for example.
Claude also offers a summary that contains all of its memories in one place, where they can be viewed and edited by the user.
Memory is an optional setting, and users have full control over what Claude remembers. Alongside memory, Anthropic also announced an Incognito mode where chats won’t be saved to memory or appear in conversation history.
Anthropic also says it ran extensive safety testing on memory, such as whether memory could potentially reinforce harmful conversation patterns, lead to over-accomodation, or enable attempts to bypass safeguards.
