Claude Cowork finally remembers what you told the app in chat

Anthropic has merged the memory systems of Claude chat and Claude Cowork, eliminating the need for users to repeatedly rebrief the AI across different product areas. The update, announced Tuesday, means that information learned in one context is now automatically available in the other, creating a more continuous assistant experience.

What changes with Claude’s memory?

Previously, users had to manually transfer context from chat conversations to Cowork, which was time-consuming and frustrating. Now, Claude remembers details from past interactions across both chat and Cowork, so users can seamlessly move from research to action without repeating themselves. For example, if a user discussed a conference’s headcount, city, and speakers in chat, Cowork will already know these details when drafting an agenda or update.

How does the new memory system work?

Claude now adds to its memory in real-time as users chat, rather than summarizing a conversation at the end. This means memories are updated instantly and shared between chat and Cowork, even during an ongoing conversation. Anthropic also provides transparency by allowing users to view, edit, or delete any saved memory, giving them control over what the AI retains.

Privacy and sensitive data handling

By default, Claude will not store personal or sensitive information such as health data, race, ethnicity, religious beliefs, politics, or gender identity. Users can opt in to allow such data by toggling on “include sensitive in memory.” The app will notify users whenever a sensitive topic is saved. Certain information, including government-issued IDs, Social Security numbers, criminal history, and immigration status, will never be stored, in line with Anthropic’s acceptable use policy.

Availability and rollout

The memory feature is enabled by default for Free, Pro, and Max plans across web, desktop, and mobile. iOS and Android users need to update their apps to the latest version to access the new functionality.

Why this matters

This update addresses a common pain point for AI users: the need to constantly re-explain context. By unifying memory, Anthropic improves efficiency and makes Claude feel like a single, coherent assistant rather than two separate products. It also gives users more control over their data, which is crucial for trust in AI systems.

Conclusion

Anthropic’s integration of memory across Claude chat and Cowork represents a meaningful step forward in AI usability. By eliminating repetitive rebriefing and offering transparent memory management, the company enhances the user experience while respecting privacy boundaries. As AI assistants become more integrated into daily workflows, such features are likely to become standard expectations.

FAQs

Q1: How do I access the new memory features?
Memory is enabled by default on all plans. Simply update your Claude app on iOS or Android to the latest version, and the feature will be active.

Q2: Can I control what Claude remembers?
Yes, you can view, edit, or delete any saved memory at any time. Additionally, you can opt in or out of storing sensitive information via the settings.

Q3: Will Claude ever store my Social Security number?
No, Claude will never store government-issued IDs, Social Security numbers, criminal history, immigration status, or other data that violates Anthropic’s acceptable use policy.