Claude memory saves and updates individual topics as you chat, so it can use relevant details in future conversations without treating each finished chat as a single summary. On Free, Pro, and Max, memory is on by default across Claude on the web, desktop, and mobile. You can inspect, edit, pause, import, export, or delete memories in Settings > Memory; deleting a chat alone does not delete the memory entries it produced.
How Claude memory works
Claude saves information as individual topics and can update those entries as conversations continue. It may save information automatically or when you ask it to remember something. Anthropic’s Claude Help Center release notes described the change on July 10, 2026: “Memory on Claude now works as a set of individual, categorized entries that Claude reads and updates during your conversations, replacing the previous daily memory summary.”
![Claude AI for Beginners Bible: [5 in 1] The Ultimate Guide to Automate Your Work, Save Hours Every Week, and Use AI for Real-World Results](https://m.media-amazon.com/images/I/415+fSJacsL._SL160_.jpg)
That means memory is not simply a recap written once when a chat ends. Claude can read and update relevant entries during later conversations. Memory is distinct from your chat history: the history contains conversations, while memory contains saved information intended to help across chats.
Projects keep separate memory
Each Claude project has its own memory space and project summary. This separation helps keep context for one project from being mixed with another project’s context.
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteWhich Claude plans have memory?
As of October 7, 2026, availability depends on the plan and, for organizational plans, the organization’s settings.
| Plan | Memory availability |
|---|---|
| Free | On by default |
| Pro | On by default |
| Max | On by default |
| Team | An organization owner must enable it; users then manage their own setting |
| Enterprise | An organization owner must enable the organization-level capability; users then manage their own setting |
On Free, Pro, and Max, memory is available on Claude web, Claude Desktop, and Claude Mobile. Use the latest mobile app version to access the feature there. If you are on Team or Enterprise and do not see memory, ask your organization owner whether it has been enabled.
How to view, edit, pause, or delete Claude memory
Open Settings > Memory to see Claude’s saved topics. From there, you can open an entry to edit or delete it, or use the available controls to pause or reset memory.
- Inspect: Review the saved topics Claude can use.
- Edit: Open a topic and change its contents.
- Delete an entry: Remove a selected topic without resetting all memory.
- Pause: Keep existing entries but stop Claude from using memory and creating new memories. Chats held while memory is paused are not added later when you resume it.
- Reset: Permanently delete all memories, including project memories. This cannot be undone.
If an organization owner turns memory off, Anthropic says organizational memory data is deleted immediately.
Recommended Free Tools
What happens when you delete a chat?
Deleting or allowing a conversation to expire does not automatically remove memory entries Claude generated from it. To remove those details, go to Settings > Memory and delete the relevant entries separately.
Anthropic’s retention guidance dated July 1, 2026 says deleted conversations disappear from chat history immediately and from backend storage within 30 days. Memory entries are managed separately, so deleting a conversation and deleting what Claude remembers from it are different actions. Memory data is included in data exports.
Does Claude remember sensitive information?
By default, Claude does not store sensitive topics such as health, race, ethnicity, religion, politics, or gender identity in memory. You can opt in through the Include sensitive topics in memory setting. That choice applies to information saved after you enable it; it does not add sensitive details from earlier chats retroactively. Claude displays a notice when it saves a sensitive topic.
Even when the setting is enabled, Claude says it will not save certain information, including government ID numbers, criminal history, financial account numbers, immigration status, and information prohibited by its safety policy.
Free tools Windows power users keep installed
One-click scans. No signup required.
Use Incognito for chats that should not enter memory
Incognito chats are available on Free, Pro, Max, Team, and Enterprise. They do not enter Claude memory or chat history. Anthropic also says Incognito chats are not used to improve Claude, even if model-improvement sharing is enabled.
Can Claude share memory with Cowork?
Chat memory and Claude Cowork memory are shared when Cowork runs in the cloud. Local Cowork sessions running on your computer do not use chat memory. Project memory remains separate for each project.
Can you import memory from ChatGPT or another AI?
Claude provides an import flow at Settings > Memory > Start import. Paste exported text from another AI provider; Claude extracts information into individual memory entries that you can review. Anthropic describes imports as experimental and warns that imported personal details unrelated to work may not be retained. Review the resulting entries rather than assuming the import copied everything exactly.
You can also export memory. To see the entries as Claude sees them, review the memory settings or ask Claude: “Write out your memories of me verbatim, exactly as they appear in your memory.”
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Scan for outdated or missing drivers - takes under a minute3Clear out junk files and repair common Windows errorsBest Value
Memory, conversation privacy, and model improvement
Memory controls do not replace Claude’s separate conversation-retention and model-improvement settings. Anthropic’s consumer privacy article, dated March 16, 2026, says data is encrypted in transit and at rest. It also says employees generally cannot access conversations unless a user consents to sharing or a Trust & Safety review is required.
Anthropic’s July 1, 2026 retention article says that if you allow model improvement, data may be retained in de-identified form for up to five years in model-training pipelines. Turning model-improvement sharing off prevents future use, subject to training that is already underway. These rules concern conversation data; saved memory entries have their own controls in Settings > Memory.
Claude.ai memory is different from the developer memory tool
Anthropic also documents a platform memory tool for developers. It is client-side: Claude requests memory operations, while the application executes them against storage it controls, commonly files under /memories or an application database. The documentation says the tool is available on Claude 4 and later models and requires applications to reject paths outside /memories to prevent path-traversal attacks.
This developer tool is not the same feature as consumer memory in Claude.ai. Its storage and behavior depend on the application using it, rather than on the consumer controls in Claude’s settings.
Quick wins for a faster PC:
Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Clear out junk files and repair common Windows errorsFree Scan →Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
