Does Claude Remember Past Conversations?

Yes, Claude can remember information across separate conversations, but only within your own Claude account and only when memory is turned on. Anthropic has made memory available to all Claude users — free, Pro, Max, Team, and Enterprise plans — on the web, Claude Desktop, and Claude Mobile, per the Claude Help Center. It works by generating a synthesized understanding of you from your chat history and carrying that context into new conversations.

That one-line answer hides some distinctions worth drawing out. Memory on Claude is a small system of related controls, not a single switch, and it behaves differently from the short-term context inside a single chat. This article sets out what Claude actually retains, how to inspect and manage it, one capability that is distinctive to Claude — moving your memory in and out as plain text — and where its memory stops.

What Claude actually remembers

According to the Claude Help Center, Claude "creates automated summaries of conversations" and generates "memory based on your chat history." Those summaries update "every 24 hours" and provide context for new standalone conversations. In practice this means Claude is not copying your old chats forward verbatim; it is carrying a distilled understanding of you into the next chat.

The same documentation notes that Claude's memory focuses on work-related content: your role, projects, and professional context; your communication preferences and working style; your technical preferences and coding style; and the details of ongoing work. Anthropic states Claude may not retain "personal details unrelated to work," so the memory is oriented toward being a useful collaborator rather than a general diary of your life.

If you use projects, memory is scoped to them. Anthropic states that each project has "its own separate memory space and dedicated project summary, so the context within each of your projects is focused, relevant, and separate from other projects," per the Claude Help Center. Work you do in one project does not bleed into the summary of another.

How to see and control it

Every control lives under settings, and Anthropic documents the paths.

The main toggle is at Settings → Capabilities, per the Claude Help Center. From there you can also "View and edit memory" to see everything Claude currently remembers about you. You can add to that memory by telling Claude in conversation what to remember, and edits "immediately apply to your next conversation," so a correction takes effect right away rather than waiting for the next daily summary.

There are two distinct ways to turn memory off, and the difference matters. Pause memory keeps Claude's existing memory intact but stops it from using that memory or making new memories — useful when you want a clean slate temporarily without discarding what Claude has learned. Reset memory "permanently deletes all memories including project memories" and, per Anthropic, "cannot be undone." Pause is reversible; reset is not.

Chat search vs. memory

Claude offers two related but distinct capabilities, and it is easy to conflate them.

Chat search lets Claude search your previous conversations to find and reference specific information on request. Memory is the synthesized understanding Claude carries into new chats on its own. The Claude Help Center frames them as related but separate: search is a lookup you invoke, while memory is the standing context that shapes new conversations without you asking. Turning one off does not turn off the other.

Memory portability: export and import

One feature sets Claude apart from most assistants: your memory is not locked in. Anthropic lets you move it as plain text.

You can export Claude's memory as plain text through settings, per the import and export documentation. You can also import memory that you exported from another AI provider: go to Settings → Capabilities → Memory section → "Start import," paste the text, and click "Add to memory." Importable content includes instructions about your response style, personal details such as name, location, job, family, and interests, your projects, goals, and recurring topics, the tools, languages, and frameworks you use, and preferences or behavioral corrections you have given.

Two caveats. Anthropic states that "memory imports are experimental and still in active development," and that Claude "may not always successfully incorporate imported memories" — treat an import as a helpful head start, not a guaranteed transfer. Imports are available on Free, Pro, Max, and Team plans on the web and Claude Desktop, per the same documentation.

What Claude's memory does not do

Memory has real boundaries, and knowing them prevents both false expectations and false worries.

It is bound to your account. Memory is a feature of Claude tied to your own account and its settings. It does not follow you to a different company's assistant or any tool outside Claude, and there is no mechanism by which it does so. If you switch products, you start from zero.

Projects are isolated from each other. As noted above, each project has its own separate memory space and dedicated summary, per the Claude Help Center. Memory built inside one project stays within that project's context.

Incognito chats deliberately remember nothing. For a conversation you do not want retained, Claude offers incognito chats. In an incognito chat, per the incognito chat documentation, "Claude won't remember your chats, so they won't be saved to Claude's memory or your chat history." You start one via a ghost icon when beginning a chat outside a project. It is the appropriate way to ask a one-off question without touching your memory state.

For context, Anthropic first announced memory publicly oriented toward teams before broader availability, per its announcement. The consumer-facing controls described here reflect where the feature has since landed across plans.

Memory vs. context window

The most common confusion is between memory and the context window, which are distinct.

The context window is the working span of text the model can see within a single conversation: your current messages plus the model's replies, up to a size limit. It is short-term and local. When a conversation grows long enough, earlier turns fall outside that window and the model can no longer see them directly. This is not memory in the feature sense; it is the model's immediate attention, and it resets when you start a new chat.

Memory is the persistent layer that survives across separate conversations. Claude's synthesized understanding is pulled into new chats as relevant context, which is why Claude can carry your working style or project context into a brand-new conversation even though that conversation's context window started empty. A concise way to hold the distinction: the context window is what Claude can read in front of it right now, and memory is what it carries in from before. Losing track of something mid-conversation is usually a context-window limit, not a memory failure.

FAQ

Does Claude remember me between separate conversations? Yes, if memory is on. Claude generates a summary of your chat history that updates roughly every 24 hours and carries that synthesized understanding into new conversations, per the Claude Help Center. If memory is off, each conversation starts blank.

How do I make Claude forget something? Open Settings → Capabilities to view and edit your memory, and remove the detail directly; edits apply to your next conversation. To clear everything, use Reset memory, which permanently deletes all memories including project memories and cannot be undone, per the Claude Help Center. If you only want a temporary pause without deleting anything, use Pause memory instead.

Can I move my Claude memory somewhere else, or bring memory in? Yes. You can export Claude's memory as plain text and import memory exported from another AI provider, via Settings → Capabilities → Memory section, per the import and export documentation. Anthropic notes imports are experimental and may not always be incorporated successfully.

Is memory the same as Claude's context window? No. The context window is the short-term text the model can see within one conversation, and it resets each chat. Memory is the persistent layer that survives across conversations. Forgetting something mid-chat is usually a context limit, not a memory setting.