--- title: "Anthropic puts persistent memory into Claude Cowork" url: https://daily.dev/posts/anthropic-puts-persistent-memory-into-claude-cowork-iep2ckjpj source_url: https://sdtimes.com/ai/anthropic-puts-persistent-memory-into-claude-cowork type: article source: "SD Times" published: 2026-08-25T18:01:15.090Z updated: 2026-08-26T11:07:24.664Z tags: ["ai-agents", "privacy", "anthropic"] reading_time: 3 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Anthropic puts persistent memory into Claude Cowork **[SD Times](https://daily.dev/sources/sdtimes)** · 3 min read · 0 upvotes · 0 comments ## Summary Anthropic has added the persistent memory feature from Claude's chat product into Claude Cowork, letting the assistant retain context across sessions—like knowing a manager's preferences or a project's headcount—without users re-prompting. Memories are stored as editable/deletable files under Topics in Memory settings, and any correction propagates to future conversations. Sensitive topics like health, ethnicity, race, and gender identity are excluded by default, and even when a user opts in via 'include sensitive topics in memory,' Claude still refuses to store sensitive PII such as SSNs, government IDs, criminal history, or immigration status. Users get a notice whenever a sensitive topic is saved, and such memories apply only going forward. Memory is on by default; sensitive topic saving is off by default. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Does Claude Cowork remember context from previous conversations now? Yes, Anthropic added persistent memory to Claude Cowork, the same memory system used in Claude's chat product. It retains context accumulated over months of interactions, so users no longer need to re-explain details like team structure, project budgets, or how metrics are defined in every new conversation. _Track how AI coding assistants evolve their memory and context handling with daily.dev._ ### What sensitive personal data will Claude never store in memory, even if I enable sensitive topics? Claude will not store sensitive PII such as Social Security numbers, government IDs, criminal history, or immigration status, even when the 'include sensitive topics in memory' setting is turned on. By default, topics like health, ethnicity, race, and gender identity are also excluded unless that setting is explicitly enabled. _Developers weighing AI privacy trade-offs can follow policy details like these on daily.dev._ ### How do I control or turn off what Claude Cowork remembers about me? Memory can be managed through Settings > Memory, where conversations are stored as files that can be read, edited, or deleted under Topics in Memory. The persistent memory feature is on by default, while saving sensitive topics is off by default and requires explicit opt-in. _Anyone configuring AI assistant settings can keep up with these controls via daily.dev._ ## Similar posts on daily.dev - [Anthropic expands memory to all paid Claude users](https://daily.dev/posts/anthropic-expands-memory-to-all-paid-claude-users-5azjjkmt2) · SD Times · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#privacy](https://daily.dev/tags/privacy), [#anthropic](https://daily.dev/tags/anthropic) [View this post on daily.dev](https://daily.dev/posts/anthropic-puts-persistent-memory-into-claude-cowork-iep2ckjpj)