GoKawiilAnthropic unifies Claude's memory across chatbot and Cowork agent
Anthropic now lets Claude share memories between its chatbot interface and Cowork, its cloud-based computer-use agent, so context from regular chats carries into automated tasks and back. The update also adds a toggle letting users allow Claude to remember sensitive topics like health or politics, which are excluded by default, with notifications each time such a memory is stored.
GoKawiil's interpretation of the reporting above, not reported fact.
Unified memory reduces repetitive re-explaining as users shift between conversational and agentic modes, making Cowork's automation genuinely more personalized rather than starting from scratch each session. Giving explicit control over sensitive-topic memory also signals Anthropic's attempt to balance personalization with privacy concerns as AI assistants retain more personal data.
- Memory now syncs between Claude chatbot and Claude Cowork sessions.
- New opt-in toggle allows Claude to remember sensitive topics like health and politics.
- Users can edit, delete, or disable memory features at any time.
Source: engadget.com — Igor Bonifacic, 2026-08-25
Published there as: “Claude's memory now works across both chats and Cowork sessions”
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.