Anthropic announced on Tuesday that it is merging the memory systems for Claude's chat and Cowork features. This update aims to eliminate the need for users to repeatedly brief the AI on projects, preferences, and other context.
The change allows Claude to retain information learned in one area and apply it when engaging in another. Users will also be able to read, edit, or delete information that Claude has stored in its memory.
This update is intended to improve the user experience by allowing a more seamless transition between research and action phases. For example, Claude Cowork could understand references like headcount, city, and speakers for a conference based on prior chat conversations.
Claude will now add topics to its memory as conversations progress, rather than summarising them at the end. While the memory feature is enabled by default across various platforms and plans, users on iOS and Android will need to update their apps.
By default, Claude will not store personal or sensitive information, but users can opt to enable the inclusion of sensitive topics in memory. However, certain information, such as government-issued IDs, criminal history, or immigration status, will not be saved.