Anthropic Unifies Claude Chat and Cowork Memory Systems
Anthropic announced Tuesday that it is merging the memory systems used by its Claude chat product and Claude Cowork, according to TechCrunch. The change means Claude will retain what it learns in one interface and apply that knowledge when a user switches to the other, removing the need to repeat context when moving from research to action.
TechCrunch reported that Anthropic is also giving users visibility into what Claude has stored, with options to read, edit, or delete information on any topic. The company said Claude will now add details to memory continuously during conversations rather than only summarizing a chat after it ends, allowing updates to sync faster between the two products.
Anthropic gave an example in which a user drafting a manager update or a conference agenda would not need to re-enter details such as headcount, location, or speakers if those had already come up in earlier chats, according to the report.
By default, Claude will not store sensitive categories of personal information, including health data, race, ethnicity, religious beliefs, political views, or gender identity, TechCrunch reported. Users can opt in to sensitive-topic memory through a toggle, and the app will notify them when such information is saved. Anthropic said Claude will never retain certain data outright, including government-issued ID numbers, Social Security numbers, criminal history, or immigration status, citing its acceptable use policy.
The unified memory feature is enabled by default for Free, Pro, and Max subscribers across web, desktop, and mobile, per TechCrunch. Mobile users on iOS and Android will need to update to the latest app version to access it.
Based on reporting by techcrunch.com.
