Anthropic unifies Claude memory across chat and Cowork

The memory Claude uses in chat is now the same one it uses in Claude Cowork. "Starting today, the memory you use in chat is the same as in Claude Cowork. Now, wherever you work with Claude, it starts from what it already knows about you," Anthropic writes on the Claude blog.

The feature ships on by default for Free, Pro, and Max users on web, desktop, and mobile. Team and Enterprise get a different posture: admins control availability, and "memory is off for individual users until they turn it on."

Instead of summarizing at the end of a session, "Claude now adds topics to memory as you chat." Everything it keeps is exposed as editable text. From the post: "Everything Claude remembers is in a list of files under Topics in Memory settings, where you can read, edit, or delete each one."

Sensitive categories are held back unless a user opts in. By default Claude "does not store topics related to personal or sensitive subject matter, like your health, race, ethnicity, religious beliefs, politics, gender identity, and other similar areas." Even with the opt-in on, some categories stay off-limits: SSNs and other government ID numbers, criminal history, immigration status, and anything violating the Acceptable Use Policy.