Big Idea

The argument in one line.

Claude's memory now syncs automatically between chat and Cowork so context built in one carries into the other, but that sync only happens when Cowork runs in the cloud, not when it runs locally on your computer.

Who This Is For

Read if. Skip if.

READ IF YOU ARE…

You already use both Claude chat and Claude Cowork and got tired of re-explaining the same context in each one.
You want Claude to remember your preferences, ongoing projects, or recurring tasks without repeating yourself every session.
You run Cowork tasks locally on your machine and need to know why your memory isn't showing up in chat.

SKIP IF…

You only use Claude chat and never touch Cowork — the shared-memory feature doesn't change anything for you.
You're on a Team or Enterprise plan where admins control memory availability and it hasn't been turned on for you yet.

TL;DR

The full version, fast.

Anthropic merged Claude's memory system so chat and Cowork now draw from the same pool of saved context instead of each product remembering you separately. Memory is created continuously as you chat rather than summarized at the end of a conversation, and it's organized into editable topic files (profile, preferences, recurring subjects) you can view, edit, or delete from Settings > Memory. It's on by default for Free, Pro, and Max plans across web, desktop, and mobile, and does not yet extend to Claude Code. The one catch: Cowork only shares memory with chat when a task runs in the cloud. A Cowork task run locally on your own computer never touches that shared pool, so the fix when syncing looks broken is checking which mode Cowork ran in.

Free for members

Chat with this breakdown — free.

Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.

Create a free account →

Chapters

Where the time goes.

00:00 – 00:22

01 · Claude's New Memory System

Cold open stating the thesis: Anthropic merged Cowork and chat memory into one system, fixing Cowork's biggest complaint.

00:22 – 01:24

02 · Breaking Down Anthropic's Announcement

Reads Anthropic's own headline and framing: memory now works everywhere, and the user decides what's in it.

01:24 – 02:01

03 · You Control What Claude Remembers

Memories are viewable and editable topic-by-topic; sensitive topics like health and beliefs are excluded by default.

02:01 – 02:41

04 · One Memory Across Cowork and Chat

Context built in Cowork now carries into chat and vice versa, closing months of re-explaining.

02:41 – 03:15

05 · How Memories Get Created Now

Claude now writes memory continuously during a conversation instead of summarizing at the end.

03:15 – 03:56

06 · Viewing and Editing Saved Memories

Saved memories are short editable files grouped by topic (profile, preferences, meal planning, etc.).

03:56 – 04:10

07 · Who Gets It (Free, Pro, Max)

Shared memory is on by default across Free, Pro, and Max plans, web, desktop, and mobile.

04:10 – 04:32

08 · What About Claude Code?

Responds to a Twitter question: as of this release, sync is chat and Cowork only, not Claude Code.

04:32 – 05:32

09 · How to Turn It On in Your Account

Live demo enabling shared memory via the settings prompt in both the browser and desktop app.

05:32 – 06:46

10 · Finding Your Stored Memories

Navigates Settings > Memory to show the accumulated Profile, Preferences, and Topics files built up over months.

06:46 – 07:37

11 · Editing a Memory in Real Time

Demonstrates correcting a saved clothing-preference memory just by typing the correction in chat.

07:37 – 08:38

12 · The Big Caveat: Cloud Only

The reveal: shared memory works everywhere except a Cowork task running locally on your own computer.

08:38 – 10:15

13 · Testing the Shared Memory Both Ways

Live test: a chat-saved memory shows up inside a cloud Cowork task, and a Cowork-saved memory shows up back in chat.

Atomic Insights

Lines worth screenshotting.

Claude's memory now draws from one shared pool across chat and Cowork instead of each product remembering you separately.
Claude adds memory continuously as you chat instead of summarizing the whole conversation after it ends.
You never have to say 'remember this' — new memory writes happen automatically mid-conversation.
Saved memories live as editable files organized by topic, and you can open, edit, or delete each one individually.
Sensitive topics like health and beliefs are excluded from memory by default and have to be turned on manually in Memory settings.
Shared memory is on by default for Free, Pro, and Max plans across web, desktop, and mobile as of this release.
Team and Enterprise admins control whether memory is available to their org, and it stays off for individual users until turned on.
The shared memory system does not extend to Claude Code as of this release, only chat and Cowork.
Cowork tasks only contribute to and pull from the shared memory pool when they run in the cloud, never when they run locally on your computer.
A Cowork task can pull a memory saved days earlier in chat mid-task, even when the task has nothing to do with the original context.
Editing a saved memory is just a chat interface: type a correction in plain language and Claude rewrites the relevant memory file.

Takeaway

One setting decides whether Claude actually remembers you.

WHAT TO LEARN

Claude's memory now follows you between chat and Cowork automatically, but only if Cowork is set to run in the cloud, not locally.

02Breaking Down Anthropic's Announcement

Claude's memory used to live separately in chat and Cowork, and Anthropic just merged them into a single shared system across both products.
Memory now works from what Claude already knows about you the moment you open a new conversation, instead of starting blank.

03You Control What Claude Remembers

Sensitive topics like health conditions or beliefs are excluded from memory by default, and you have to opt in manually if you want them tracked.

04One Memory Across Cowork and Chat

Whatever Claude picks up from a Cowork task now carries back into chat, and whatever you tell chat is available the next time you hand Cowork a task.
This closes months of context gaps: a status update, a recurring project detail, or a client's preferences no longer has to be re-explained in each product separately.

05How Memories Get Created Now

Claude now writes memory continuously during a conversation instead of summarizing everything after it ends, so mid-conversation details get captured immediately.
You never have to say 'remember this' for it to stick; the system decides on its own what's worth saving as you go.

06Viewing and Editing Saved Memories

Every stored memory is a short, individually editable file grouped under a topic, so fixing one wrong detail doesn't require deleting the whole history.

07Who Gets It (Free, Pro, Max)

Shared memory is on by default across Free, Pro, and Max plans on web, desktop, and mobile, so most users already have it active without doing anything.

08What About Claude Code?

As of this release, shared memory only covers Claude chat and Cowork; Claude Code is not part of the synced pool yet.

09How to Turn It On in Your Account

Turning it on is a single settings prompt: accept the default, or opt in separately to letting Claude store sensitive topics too.

10Finding Your Stored Memories

Memories live under Settings > Memory, broken into categories like Profile, Preferences, and individual recurring Topics (clothing, finances, fitness, community, and more).
The list grows the more you use Claude across both chat and Cowork, since every recurring subject you mention eventually gets its own topic file.

11Editing a Memory in Real Time

Editing a memory is just a conversation: type the correction in plain language and Claude rewrites the relevant file, no manual file editing required.
A follow-up detail added to an existing topic (like a clothing preference) appends onto that file instead of creating a duplicate or conflicting entry.

12The Big Caveat: Cloud Only

Shared memory only works when a Cowork task runs in the cloud; a task run locally on your own computer never touches or contributes to it.
This is the setting most likely to make the whole feature look broken: if Cowork is set to run locally, nothing it learns will show up in chat.

13Testing the Shared Memory Both Ways

A memory saved in chat mode was retrievable inside a cloud Cowork task seconds later, confirming the sync works even when the task has nothing to do with that memory's original topic.
The reverse also worked: a preference saved mid-task inside Cowork showed up immediately when asked about in chat, confirming the sync runs both directions, not just one.

Glossary

Terms worth knowing.

Cowork: Anthropic's agentic Claude product that can run multi-step tasks against your files and folders, either locally on your computer or in the cloud.
Shared memory: The new system where Claude chat and Claude Cowork read from and write to the same saved-memory pool instead of remembering you separately in each product.
Cloud task: A Cowork task set to run on Anthropic's servers rather than your local machine, which keeps running after you close the app and is the only mode that syncs with shared memory.

Resources

Things they pointed at.

05:32toolClaude Memory settings (Settings > Memory)

08:38toolClaude Cowork cloud task mode

Quotables

Lines you could clip.

00:00

“Anthropic just dropped a new Claude memory system that basically combines the memory of Claude Cowork and Claude Chat into one.”

cold open hook that states the whole video in one sentence→ TikTok hook↗ Tweet quote

02:51

“Claude now adds topics to memory as you chat instead of summarizing a conversation at the end.”

crisp one-line explanation of the core mechanism change→ newsletter pull-quote↗ Tweet quote

07:37

“All of these memories are saved everywhere except right here.”

the twist moment that sets up the rest of the demo, high curiosity→ IG reel cold open↗ Tweet quote

The Script

Word for word.

Read-along

Don't just watch it. Burn it in.

See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.

metaphor

Anthropic just dropped a new Claude memory system that basically combines the memory of Claude Cowork and Claude Chat into one. And if you've ever used Claude Cowork, one of the negatives about it is it had very bad memory. Well, this solves it.

So in this video, I'm gonna break down exactly what's new, how to turn this on inside of your account, and then I'm gonna break down one big caveat that we need to talk about so you could fully understand how this works. Let's dive in. Alright.

So first things first, let's dissect this article that Anthropic just released talking about the new shared memory between Claude Cowork and Claude chat mode. There's a few key things here that is actually really interesting, and then not only am I gonna talk about this, but I'm gonna dive into Claude Cowork and show you exactly how this works.

First of all, the headline for this is Claude's memory works everywhere, and you decide what's in it. This is kind of the main headline right here, the fact that we could decide what Claude actually remembers, and I'm gonna show you exactly how to do this later on in this video, so make sure to stick to the end.

Now starting today, the memory you use in chat is the same as Claude Cowork. Now wherever you work with Claude, it starts from what it already knows about you. If you've used Claude Cowork in the past, unless you're working in a particular project, it usually doesn't remember you or everything about your business in the previous conversations you had, and this is one of the reasons why a lot of people were only using Claude chat mode instead of co work because we didn't have this persistent memory on us in our previous conversations.

Now it says you can see everything Claude remembers topic by topic and edit or delete any of it. So it almost acts as a second brain now directly inside of Claude that we have access to. And, again, we can make changes to what it remembers, so we could kind of enrich these memories that it has on us.

And this is an interesting point right here for privacy concerns. Claude does not store subjects considered sensitive, like health or beliefs, to memory by default. But if those are topics you were tired of re reexplaining, you can turn them on inside of the memory settings.

So it's cool that we could customize, you know, the thing the personal things that Claude remembers about us if we wanna give it more context, which for me, I have no problem doing. One memory across Claude Cowork and chat. Cowork now has memory, and it's the same one that you use in chat, leading to less explaining and picking up where you left off.

When Cowork runs a task in the cloud, what Claude remembers from the chat is there and vice versa. The context you've built up across months of conversations, for instance, your q three priorities, and the status of your projects is there the moment that you hand co work a task, and what comes up in co work carries back to chat.

So this works both ways. If we're interacting with Claude co work and we say something in particular that maybe we're working on for the day, when we go back over to Claude chat mode, it's gonna have that persistent memory there as well. Now this is a pretty interesting point here.

The way that it creates these memories is different than in the past, so let me break this down right now. Claude now adds topics to memory as you chat instead of summarizing a conversation at the end.

So if we're in the middle of a conversation and we say something specific that Claude needs to remember, it will know that it needs to store that as a memory instead of waiting for the whole conversation to go on and then coming up with the TLDR points that we that we need to save as a memory. So this seems like it'll be much more efficient, and we don't have to say things like, remember this.

It's just automatically gonna add these different memories to our system. Now this is the point that's probably the most interesting about this whole release. We can see and edit our saved memories, as you can see here.

So in this example, it shows a couple of different key topics here. So it shows your profile, your preferences, topics, specific things like meal planning, client pitching, half marathon training, etcetera. We could even click on these files and go and edit them manually to change certain things about them, or we could delete them if it's sensitive information that we don't want Claude to have on us.

And then this is what it looks like when we click on those memories. So we can just chat with it in this simple chat user interface and tell Claude exactly what it is that we would like to change, or I could imagine we could literally click inside of here and make changes to this like it's a markdown file. Now this is great news for everybody because this is now on by default for the free plan, pro plan, and the max plan across the web, desktop, and mobile.

So, basically, everybody's gonna have access to this no matter what plan you're on. Now I did see this reply on Twitter, so I figured I would address this point right here. This guy is asking, what about Claude Cowork and Claude Code and vice versa?

As of right now, this is only syncing between Cowork and chat mode. There is no way for us to have a shared memory between Cowork and Claude Code. But if I had to guess, this is probably something that they're working on that will probably be rolling out over the coming weeks or months, but that's just my speculation.

Alright. So now let me show you exactly where we can find this inside of our Claude account. First of all, if I come to claude.ai in my browser, you can now see when I open my account, I'm gonna see this right here.

So it shows that Claude remembers co work tasks too. We can see all the memories that it saved as a file, and then it shows that we have more control over specific sensitive topics. So I could either click not now if I don't wanna enable this, but I'm just gonna go ahead and click save preferences.

For me, personally, I'm just gonna toggle this on so it includes sensitive topics inside of memory, but, obviously, do your own due diligence and maybe toggle that off if you're skeptical. So I'm just gonna clickly now, select save preferences.

And this is the interface that we're gonna see inside of Claude. And, obviously, we have chat mode right here and co work, which now have a which now have a shared memory across both of these products. Now we're gonna see the exact same thing inside of the Claude desktop app, which you're looking at right here.

So, again, I'm gonna have this exact same prompt here that I need to fill out, and I'm just gonna go and save my preferences. And now let me show you how to find our memories that Claude already has stored. So if I come down to my profile at the very bottom, I'm gonna click on this account.

I'm just gonna click on this and then click on settings. And if I scroll down to the very bottom, we're now gonna see this memory button right underneath our plug ins. So I'm gonna click on memory, and here are some of the memories that it saved for me over the past couple of months.

And as of right now, these are just my chat memories. We're gonna see a few things. So first of all, I could come here and click import memory from other AI providers.

So if I wanna import our memory from Chatcha b t or Gemini, for example, I can do that right here. Next up, it breaks these down by categories, which I find is pretty cool. So for example, it shows my preferences, which is one specific file here, Shows my profile, and then here are all the different topics.

So it has my clothing fit preferences. It has my school community topics. It has finances, fitness, photography, podcast, reading, tools.

All of these are broken down by topics. And as I interact with Claude more and more on both co work and chat mode, these topics are gonna expand and the people that I work with or mention quite often. As you can see, Aidan right here is my business partner, and it remembered him.

Now let me click on one of these to show you what it looks like. So if I click on clothing, this is a very simple memory. It just shows specific hoodie fit that I like, and it even shows the details of me and the types of men's hoodies that I like.

So, for example, this is pretty funny. It shows that I only want men's hoodies that aren't boxy. And it even remembers me giving a complaint saying I bought an expensive hoodie, but the wrist cuffs and the waist cuffs were stretched out, and I wanna make sure this doesn't happen.

So let's say I wanna change this memory. I could just come here and say, I also wanna mention that for my shirts, I've really been into a little bit more oversized around the arms, but I don't like them to be too long. I also like just more cotton fabric.

So, obviously, I'm just getting a brain dump. I'm clicking send, and now it's going to filter this information into this specific memory file. And just like that, at the very bottom, it now added this detail for how I like my shirts.

Now there is something really important that we need to talk about, and that is that all of these memories are saved everywhere except right here. So if we turn on so if we turn on this new memory system, this works inside of Claude Cowork in chat mode, but only in the cloud. But if we're running Claude Cowork on our computer locally, then it's not gonna have this same shared memory system.

Let me explain this further if you don't fully understand the difference between it working locally on your computer versus working in the cloud. So if I come back into Claude Cowork right here, at the very top right, you're gonna see this little desktop icon, and I'm gonna go ahead and click on this. There are two different ways that we could run this task.

Either we could run it in the cloud, which is in beta, which basically keeps everything going even when we close the app on our computer, or we could close our computer, for example. But if we have this running on our computer, this only runs when our computer is on. So in order for us to have this shared memory across CloudCowork in chat mode, we need to be running this in the cloud.

Otherwise, it's not gonna work. Now this isn't the biggest of deals because as you can see here, I'm running this task in the cloud, and I could still go and select the different folders on my computer.

So for example, let me select my YouTube's video project and folder that I have on my local desktop, and I could just come here and say, hey. What is my shirt preference? I know that has nothing to do with YouTube videos, but I'm gonna send that off, and it's gonna show that that memory that we saved earlier inside of Claude chat mode will then translate, and we could access that inside of Cowork.

And just like this, it's searching the memory here. It's pulling up the clothing memory, and here's exactly what it found.

A bit more oversized around the arms, not too long in length, and more cotton in the fabric, which is exactly the memory that I saved earlier on. Let's test this on the co work side and give it a memory to create and then see if it translates over into chat mode. Alright.

So as for my pants, I kind of like my pants slightly oversized these days. Can you save that to the memory as well? Here we go.

It says it added this to the memory. If I click on the memory, you can now see that it also added these details for how I like my pants. So let's just come back to chat mode and say, hey.

Do you know how I like my pants styled? So here we go. It just pulled from that memory file, and this is syncing between Cloud Cowork and chat mode.

But, again, this has to be running in the cloud. Now not only will it store this memory inside of the desktop app like you're seeing right here, but if I pull up my phone, it would also save this memory there as well. Anyways, guys, there you have it.

If you enjoyed the video, leave a like, leave a comment, and subscribe for more content like this. This channel is AI for nontechies where I teach nontechies how to use AI. Thanks for saying the end, and I'll see you in the next video.

Peace.

The Hook

The bait, then the rug-pull.

Anthropic quietly merged two memory systems that used to work in isolation: what Claude chat remembers about you and what Claude Cowork remembers about you are now the same pool, updated as you talk instead of summarized after the fact.

Frameworks