Claude Cowork has incorporated a memory feature that allows it to retain information and share it with Claude's conversations.
The update from Anthropic aims to prevent users from having to re-explain information when switching between Cowork and the chat.
How Claude Cowork's memory works
With the new feature, Claude Cowork can remember information used during a task. This memory is shared with Claude's chat.
This means that when a user performs a task in Cowork, Claude can recall that information when returning to the chat, and it also works in reverse.
According to Anthropic, the memory now incorporates topics while users converse, instead of summarizing conversations once they end.
Users can control what Claude remembers
Previously, it was necessary to tell Claude to remember specific information. Now, the feature allows users to manage those memories from the memory settings.
The created memories appear in a list of files within Topics. From that section, users can read, edit, or delete the saved information.
Additionally, Anthropic allows users to pause or reset the memory at any time.
What sensitive information Claude does not store by default
The memory is enabled by default, but Anthropic indicated that certain sensitive data is not stored by default.
