Claude’s memory works everywhere, and you decide what’s in it
Claude’s memory now works the same in chat and in Claude Cowork’s cloud sessions. Topics are added as you chat instead of summarized after the fact. Everything sits in files under Topics, readable, editable, and deletable. Sensitive topics stay off by default.
Why it mattered One shared, live-updated memory across chat and Cowork, fully visible and editable: the end of re-explaining yourself when you switch surfaces.
Anthropic unified Claude’s memory across chat and Claude Cowork. The memory used in chat is now the same one Cowork draws on in cloud sessions, and what comes up in Cowork carries back to chat. Instead of summarizing conversations after they end, Claude adds topics to memory as you chat.
Every memory lives as a short file under Topics in Memory settings, where users can read, edit, or delete each one. Sensitive subjects like health or beliefs are not stored by default, though users can opt in. Some categories, such as ID numbers and criminal history, are never stored.