← LearnClaude.ai · Memory

How to Make Claude Remember Previous Conversations

To make Claude remember previous conversations, enable 'Generate memory from chat history' in claude.ai Settings > Capabilities. Once on, Claude automatically summarizes your past standalone chats into a persistent memory summary it references at the start of every new session.

To make Claude remember previous conversations, go to Settings > Capabilities on claude.ai and toggle on Generate memory from chat history. Claude will then automatically build a persistent memory summary from your past standalone chats and reference it at the start of every new session — so you never have to re-explain your role, preferences, or ongoing projects again.

What Is Claude's Memory Feature?

Generate memory from chat history is a feature on claude.ai that automatically summarizes your past conversations and builds a persistent memory summary that Claude references at the start of every new standalone chat. Rather than starting each session cold, Claude extracts key facts about your preferences, work context, and ongoing projects from your conversation history and maintains them in a structured profile.

This means you no longer need to re-explain your background, writing style, technical environment, or recurring goals at the start of each new conversation. The memory synthesis runs as a background process that updates within 24 hours whenever conversations are created, modified, or deleted.

For full details, see Anthropic's official guide on using Claude's chat search and memory.

How Do You Enable Claude's Memory?

Enabling memory takes under a minute. Here's exactly how to do it:

  1. Click your user avatar or profile icon in the top-left corner of claude.ai.
  2. Select Settings from the dropdown menu.
  3. In the left sidebar, click Capabilities.
  4. Locate the Generate memory from chat history toggle and switch it to On.
  5. Claude will begin synthesizing your past standalone chats into a memory summary; this initial generation may take up to 24 hours.
  6. To verify it worked, open a brand-new chat and ask: "What do you know about me and my work?" Claude should describe your stored context without you repeating anything.

Once active, you can view or edit stored memories at any time by clicking View and edit your memory on the same Capabilities page, or by asking Claude directly: "Write out your memories of me verbatim, exactly as they appear in your memory."

Which Claude Plans Include Memory?

The feature is available on all claude.ai plans — Free, Pro, Max, Team, and Enterprise — across web, desktop, and mobile. Team and Enterprise administrators have additional organization-level controls. Enterprise owners can disable and permanently purge all memory data across their organization for compliance purposes.

How Is Memory Different from Projects?

This is one of the most important distinctions to understand. Memory and Projects are separate systems:

  • Standalone chats (outside of any Project) contribute to your general memory summary — the persistent profile that follows you across all your everyday conversations.
  • Each Project maintains its own isolated memory space. Context from one Project does not bleed into another, and Project memory does not mix with your general memory summary.

This separation matters in practice. If you're a consultant managing multiple clients, keeping each client's work inside its own Claude Project ensures their context stays isolated. Learn more about how to create and manage Projects on claude.ai.

What Are the Best Real-World Uses for Claude Memory?

Here are the scenarios where memory delivers the most obvious value:

  • Writers and content creators: A freelance technical writer no longer has to open every session by explaining their audience, voice guidelines, or preferred style. Claude remembers that they write for Python developers, use the Google style guide, prefer imperative voice, and flag ambiguities with comments rather than direct edits.
  • Iterative style learning: A content creator who repeatedly corrects Claude for using corporate jargon and overly long conclusions will find that, over time, Claude's memory synthesizes these corrections into standing behavioral rules — so future drafts automatically match their preferred concise, plain-language style without repeated correction.
  • Developers switching platforms: A developer who has spent months building up a detailed profile in another AI assistant can export their memory from the previous platform, paste it into Claude's memory import tool, and Claude incorporates their preferred frameworks, coding conventions, and workflow constraints without starting from scratch.
  • Enterprise consultancies: A consulting firm keeps separate Claude Projects per client. Claude remembers each client's regulatory constraints, budget parameters, stakeholder preferences, and previously rejected approaches, allowing consultants to pick up exactly where they left off.

How Do You Control What Claude Remembers?

Pausing memory

If you want to stop Claude from creating new memories without losing what's already stored, toggle the switch Off and select Pause memory. Claude will still reference your existing memory summary — it just won't add to it.

Resetting memory

To permanently delete all stored memory, toggle Off and select Reset memory, then confirm. This action cannot be undone, so use it only when you genuinely want a clean slate.

Incognito chat

For sensitive or confidential conversations you never want stored, click the ghost icon in the upper right of a new chat to open an Incognito chat session. Incognito chats are not saved to history and are never incorporated into your memory summary.

Editing individual memories

Go to Settings > Capabilities > View and edit your memory to review, edit, or delete specific entries. This is especially useful when a project ends and you don't want outdated constraints applied to new work.

When Should You Use Memory vs. Other Claude Features?

Situation Best tool Why
You want Claude to learn your preferences automatically over time Generate memory from chat history Adaptive, builds up without manual effort, follows you across all standalone chats
You have fixed, stable context that should always apply to a Project Project instructions (system prompt) Static and predictable; ideal for company style guides or defined personas
Your reference material is a discrete document (spec, codebase, report) Project knowledge base Designed for file-based content, not behavioral preferences
You need a fully isolated session with no history connection Incognito chat Nothing is saved or synthesized; ideal for sensitive or one-off topics
You're building a custom app or agent that needs programmatic memory Memory tool via the Claude API Separate developer capability; not the same as the claude.ai memory feature

What Are the Most Common Pitfalls — and How Do You Avoid Them?

Expecting memory to update instantly

Memory synthesis runs as a background process and updates within 24 hours of conversations being created, modified, or deleted. If you need Claude to use specific context right away in the same session, state it explicitly in your message or add it manually via Settings > Capabilities > View and edit your memory.

Thinking "Pause memory" gives you a blank slate

Pausing memory only stops new memories from being created. Claude still references the existing memory summary. To get a fully context-free session, use Incognito chat mode instead.

Sensitive information getting stored unintentionally

Use Incognito chat for any conversations involving confidential strategy, personal information, or client-sensitive data. Regularly audit your memory via View and edit your memory and delete any entries you did not intend to store.

Stale memory causing context drift

Periodically review your memory entries and delete anything tied to completed projects, resolved issues, or one-off formatting rules. Keeping memory lean and current prevents Claude from applying outdated constraints to new work.

Enterprise admins permanently deleting all user memory

Disabling memory at the organization level immediately and permanently deletes all memory data for all users — this cannot be reversed. Before acting, communicate to users so they can preserve critical context manually.

Can You Import Memory from Another AI Platform?

Yes. Claude includes a memory import tool that lets you transfer a memory summary from another AI assistant. You export your memory from the previous platform, paste it into Claude's import tool, and Claude incorporates your preferred frameworks, coding conventions, and workflow constraints. Note that the import feature is explicitly marked as experimental, with the caveat that imported memories may not always integrate correctly. For details, see Anthropic's guide on importing and exporting your memory from Claude.

Is Claude Memory Worth Enabling?

For anyone who uses Claude regularly for work — writing, coding, research, client management — the answer is almost certainly yes. The core value is simple: you stop paying a "context tax" at the start of every conversation. Instead of spending the first few messages re-establishing who you are and what you need, you get straight to the work.

The feature is most powerful when combined with good hygiene: periodically prune stale entries, use Incognito chat for anything sensitive, and keep client or project-specific work inside dedicated Projects. With those habits in place, Claude's memory becomes a quiet but significant productivity multiplier across your daily workflow.

Frequently asked questions

Does Claude remember conversations automatically?

Not by default. You need to enable 'Generate memory from chat history' in Settings > Capabilities on claude.ai. Once enabled, Claude automatically synthesizes your past standalone chats into a memory summary it references in future sessions.

How long does it take for Claude to update its memory?

Memory synthesis runs as a background process and updates within 24 hours of conversations being created, modified, or deleted. If you need context applied immediately, add it manually via Settings > Capabilities > View and edit your memory.

Is Claude's memory available on the free plan?

Yes. Generate memory from chat history is available on all claude.ai plans, including Free, Pro, Max, Team, and Enterprise, across web, desktop, and mobile.

How do I stop Claude from remembering a specific conversation?

Open an Incognito chat by clicking the ghost icon in the upper right of a new chat. Incognito chats are not saved to history and are never incorporated into your memory summary.

What's the difference between pausing and resetting memory?

Pausing memory stops new memories from being created but keeps your existing memory summary intact — Claude still references it. Resetting memory permanently deletes all stored memory and cannot be undone.

Does memory work inside Claude Projects?

Projects have their own isolated memory space, separate from your general memory summary. Standalone chats outside of Projects contribute to your general memory, while each Project maintains its own context independently.

Can I edit what Claude has remembered about me?

Yes. Go to Settings > Capabilities and click 'View and edit your memory' to review, edit, or delete any individual memory entry at any time.

Go deeper

Generate memory from chat history is one of 85 features in Claude Master — the independent, continuously updated manual with worked examples, the pitfalls, and the workflows that put Claude to work.

Get Claude Master — founding price

Independent product. Not affiliated with or endorsed by Anthropic. "Claude" is a trademark of Anthropic, used here only to describe the subject of this guide.