Anthropic links Claude and Cowork memory, adds real-time updates
Anthropic now shares a single memory system between Claude and its Cowork tool, so context from past chats carries over automatically when switching between them. Claude also updates its memory in real time without needing explicit prompts, and users get new controls to view, edit, delete or pause stored memories in Settings.
GoKawiil's interpretation of the reporting above, not reported fact.
Unified memory reduces repetitive context-setting for users juggling multiple Anthropic tools, making the assistant feel more continuous and personalized. The opt-in handling of sensitive topics, alongside hard exclusions for data like ID numbers and financial details, shows Anthropic trying to balance convenience with privacy risk as AI memory features become standard.
- Claude and Cowork now share the same memory, removing the need to re-explain context between tools.
- Memory updates happen automatically in real time, and users can review, edit or delete saved topics in Settings.
- Sensitive topics like allergies can optionally be remembered, but data such as ID numbers and financial details is never stored.
Source: cnet.com — Blake Stimac, 2026-08-25
Published there as: “Anthropic Unifies Memory Across Claude and Cowork”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.