Transcription
Cord memory systems are a cheat code, but only if you use them properly. And in this video, I'm going to show you exactly how to set up your own second AI brain that works across all apps with an incredibly simple setup. So, you can have a memory operating system that makes you 10 times more productive and stops wasting your time.
And if you don't know who I am, my name is Jack Roberts. I built and sold my last tech startup with the gazillion customers. Now I build my own AI businesses and I just share the stuff that actually works. So if you haven't already, grab that beautiful coffee and let's dive straight in.
So this is the Claude memory system and I've spent over a year looking at memory systems and I've done a lot of research. This is the simplest one that I've actually found. So when we talk about the Claude code memory system, what do I actually mean? What does great look like? Let's define what that is before we think about what we're going to build.
Well, the first thing that a great memory system does is it remembers everything that you say, right? Not just last 10 messages, not just the thread, every meaningful exchange that you've ever had with it. It remembers it and we can capture and refer to it whenever we want to, just like this beautiful filing cabinet here. So, the first goal is it needs to remember what we've said.
The second thing is that we can change the the important stuff on the fly, right? Maybe we don't want to focus on strategy A anymore. We want to focus on strategy B. Maybe your income's gone up and you want to change and reflect that strategy. So we need the ability to change the important stuff with your role, your stack, whatever it is. We want to be able to disregard old information.
The third thing that it needs to do, it needs to plug into every platform. This is what I call information silos. It's very common AI chatpt for this, Claude for that, maybe your grandmother's basement for something completely different. We don't want to be hip and hopping. We need a central memory system which is the universal point of truth. We call it the memory core in this system.
Fourthly, and finally, it needs to fuel every answer with context. What is the point of this memory system if we can't ask it questions about stuff that's happened? And we can't get context-rich information when we ask it things about strategy. We have a prompt. We have our three tier three-level memory system. Then we get the output. That is the basic idea.
Memory is not a vault. It's an import. Every prompt silently pulls from your stack, who you are, what you're shipping, what you decided last month. So, the response lands sharper than any fresh chat could ever hope to do.
Now, how many times have you spoken with Claude or Chat GBT to get halfway through the conversation and it's talking complete Spanish? And it's because it has amnesia. Now, the best way to solve for this is to think about your memory system as solving this across three levels. Okay? We have short-term memory, which is very simply, who am I? We have mid-term memory, which is what am I doing? And then we have long-term memory, which is what's happened before, and an expert knowledge base. I'll explain exactly what I mean.
All right. Now, not to get metaphysical, but the first question you have to ask yourself is who am I? And I'm not talking about glass of red wine at 4:00 a.m. in the morning. I mean, does your model actually know who you are? We call this the operating manual. And it's the very first level, the very first tier of our three-level memory system. So, think about it like this. Who am I? It's your name, your role, your current goals, the way you like your answers framed, the tools you use, tone, voice, non-negotiables, stuff that does not change every week, but defines every reply. So, here's me for example. My name's Jack Roberts, AI YouTuber, direct fluff, m dashes, emojis, vibe is the cheat code if I'm talking about this particular presentation.
Now, the idea of this is that it lives natively in every single platform and it grows as you talk. So the idea with claude for example has its own internal memory system which gets better over time and when you express preferences or ask it things it records that for you. So as you're actually talking to them and you say hey remember this or I prefer xz Claude will actually remember that stuff for you. But one little hack I want to show you really quickly.
So first actionable step go on Claude if you're coding Claude come to the bottom left under Jack Roberts click on obviously yours may not say Jack Roberts unless we got the same name I don't know. Come up to general and what you're looking for here is instructions for Claude. Put some stuff in here. Try to make it no more than 200 words maximum. Just top level stuff of how you want claw to behave and any key information about you. Okay.
Then if you're in anti-gravity for example, all you do is click on the additional options and you click on customization. This will be the same in VS Code and various other forks and you'll see you have global and you have workspace. You click on global and these are going to be gemini.mmd which are the global instructions for how these models basically behave with you. Now what's important to bear in mind here is that there's two bits of memory. One is the explicit hardcode stuff and then we have the generalized knowledge it has of you which it will natively pick up based on your conversations.
So this is important thing to understand with these memory systems is that the outcome of the conversation should never ever depend on a chat history. I should be able with this system and you can with this system it's why it's so cool open new chat window and regardless of any previous message it should always give me the best advice possible. But think of this level one as your general topfunnel memory that identifies who you are. It's important to bear in mind that models forget things. They get truncated. They hallucinate. If it matters, we need to make sure we're writing it down. Okay.
So, real quick, what are you doing? Well, not right now. I mean, you and I are hanging out together, but I mean, what are you working on right now? Because this is the second level of a three- tier system. It's the projects you're doing. They may change from time to time. Maybe you're building a startup. Maybe you've got a really cool client or several cool clients. These are the things that you'll be doing right now. And that forms the second level of our system. And that's why in this second level, it's actually quite structural.
So what we're going to do essentially is create six or seven separate folders for all the things that we're doing. So for example, I might have one for my community. I might have one for my agency. I might have one for my startup. And or you know, one might be personal life and health and fitness and getting like in shape and all that kind of stuff. So what you need to do first of all is head over to Claude or this could be your model of choice. I need to ask you this question. Hey, based on everything that you know about me, all of our conversation, all of our chat history and projects, I want you to organize all the areas of my life and business into six to eight different categories. It summize everything that I'm doing. I'm using this to build up folders to best organize my life and my business. And once you've got that, you can basically create it. And it is surprisingly accurate, but you don't want any more than eight, otherwise it's way too much to manage.
Now what we're going to do based on those eight things if we come down to shivers workshop and what we're effectively doing is creating one unique claude.md file for each of those eight projects. You could do it based on clients but again try to keep it under eight. All right. So we've got the claw.md at the root that tells claude what the project is. The memory folder beside it stores everything that evolves the decisions the strategies the summaries the next actions you can open up in any platform and it just works. And what I've done for you as well, I've pulled together this project operating manual that you can just literally copy and paste. And what I want you to do based on those eight things is come down and essentially create this per project. So this is opens a folder. So what happens here is that claude will open this up before it touches any of your code. So it sits as a living medium-term memory that can change based on what you're working on at the moment. It's the midterm layer of our threelevel memory system.
Okay. So what's included in this folder? We need to explain what the folder is, what the goal is, why does it exist. This exists to get me 10% body fat. This exists to make me $X,000. This exists to help my client at XYZ. The stack, what are you building it with? Decisions you've already made. Okay, so calls already made so we don't need to relitigate them. It needs to have a memory map about where each individual memory lives and any references that are relevant. Okay. Now, the template is simply this. I'll let you basically copy and paste this, but essentially fill this out for everything. Okay. And here's an example of what that might look like based on everything you're doing. Now, we want to keep it under 200 lines because this is your MD. Effectively, what this will do is be pre-filled into every single conversation. So, we don't want it to be too big. It needs to be updated, needs to be accurate, and it's one folder per repo. So, ask all the questions, copy this into these six folders, and then fill it out.
Now, if you are in claw desktop app, what you can do in co-work, if you're using coowork, is literally use what I would call the projects tab. So, you click on projects. This is their version of that. Okay, these can be your six or seven different versions. Awesome. Now, if you're in code, again, I'd recommend code honestly because it does everything that co-work does, but like it better and unlimited and it's essentially the same thing that in code, all you would do is effectively create these six or seven folders on your desktop. And when you open this up, you can see all the folders on the left hand side. And it's the exact same thing in anti-gravity. You can have all the folders basically. And all you do ever do is you open it up and you open up the folder that you want to chat in based on the conversations that you're having. And so the idea here is that whenever you do work, all you do is you think about which of the seven things is it about it's about my business. Cool. When I click on business, it's about growing my LinkedIn. Then I click on LinkedIn. And effectively, you do all your work inside that project for that specific thing. It has the living mid-term strategy that may change. It is what we call mutable. It might it is subject to change. and we do all the work in those seven project folders based on the things that you want to do.
And the third level is probably one of the most important which is it's long-term memory. And most people I've seen either drastically over complicate it or don't set it up properly, meaning they get none of the benefits but all the complexity. So level three is the arcade. It basically answers the question, what happened before? What the hell happened before this? So let's get into a little bit detail.
Now to do this, we're going to use one of two systems. Option one is going to be something called Pine Cone, which effectively is a big database. This looks really technical. You're probably thinking, Jag, this is way out of control. In reality, they're just five mystical bookshelves, which are very, very cool. In reality, what it looks like is you can ask questions to things like this and ajag.com. All of my YouTube videos, any content I ever create is indexed into this beautiful thing in Pine Cone. It is unbelievably easy to set up.
And the other alternative we have is, you might have guessed it, something called Obsidian. And obsidian itself has gained a lot of virality especially a new system what we call karpathy obsidian which was considered an alternative to what we use in pine cone which is retrieval augmented generation. Now the idea of this is that it tracks all of the text for any topic you want to. You can amend it. Claude has access to all of it in these markdown files which is really cool. And it understands basically everything. And the more that you basically use this um the better the system gets because it finds cross linkages between everything. So this one here is a for you can see this is an example one I have on YouTube and you can see the relationships between each of the individual things. I know you're thinking Jack graphs are great but will graphs solve all my problems? Um the answer to that question is yes they will. No they won't. Of course they won't. But yeah this is the idea of obsidian basically. And obviously you can do little funny things with it which is like half the fun is moving these sliders up and down basically. But this is what they call Kopathi Obsidian, which is his alternative to a complex rag system.
Now, this isn't a right or wrong. You can pick either one of these two systems that you like. Let me help you make an informed decision if I may. So, if you look at Obsidian, which is the node one that I showed you, you use this when you want to read and edit the memory by hand. So, if you want to physically look at your memories, double click in. For example, I want to click on this. I want to see what this says. I want to come down and read it. Then you may want to go for something like Obsidian. You can create strategy node, decision frameworks, visual graphs and backlinks are important to you and you want zero infer, you just want the files, Obsidian might be one for you. And I'll put a full link on screen right now if you want to double click and set up Obsidian. I go through the entire thing.
Alternatively, you have Pine Cam. If you want semantic search across thousands of records, this is way more scalable, can work anywhere. You can publish it in apps. It can be accessed from anywhere on the planet. You know, you want to store wrap-ups on every session. uh if it's for scale, so you want to store long information like books and transcripts, it is incredible for that. In other words, if you want a readable file, use Obsidian. If you want to index a searchable summary, use Pine Cone. If you're asking what I personally use, I personally use Pine Cone just because I don't want to read through everything in Obsidian, but Obsidian does really have its genuine use cases.
Now, there are two levels to long-term memory. One is an archive of any conversation that you've ever had. Now the really cool thing is whether this is include whether this is in open core hermes or any system you're using we can if we're using pine cone for example send all this information to pine cone and we can index it. So for example if I have a big conversation with this all I do is I create a skill I can come down do for/ wrap-up and I have a wrap-up skill that takes the entire conversation and embeds it in pine cone. Now, if you want to know how to set this this wrap-up skill up, I'll put a link on screen for you so you can go through my full pine cone video that breaks down the entire system for you, my capacity video.
And then the second level of long-term memory here, guys, is the what I would call knowledge, deep knowledge. So, for example, I might want to have a YouTube expertise database in my pine cone, for example. And again, you can do this with Obsidian if you like to, but the idea is this one might be YouTube, and this could be all the information that I want on for growing on YouTube, or it could be my business or whatever it is. And then what I'm doing is when I'm there having conversations, your AI agent or your AI conversation can call and reach over and conversate with this knowledge base when it's relevant.
And so in the project folder section that we covered in section two, what you might say and which is where it all interconnects together. Okay, so let's say for example that one of my folders is Glider, right? Glider is the speech of tech startup that I founded lets you yap into your computer. In the glider folder for example in here I might say look these are the indexes in pine cone I want you to consult when I ask you strategic questions this is my long-term memory in addition to that if I ask you for any history consult this index then in pine cone I might have an index over here which could be glid strategy or it could be business strategy or hormosi or whatever it is and it will call that long-term memory that expert knowledge and history to help and improve the current conversation.
Now, to actually build out that long-term knowledge, there's two systems we can do. One is to connect this to notebook LM. I'll put a link down below, but for example, I could say something like, "Hey, go and do some research on business strategy according to Alex or Mosi. Go create for me a notebook in my notebook LM and just get me like 50 different resources, as much as you possibly can, and create that notebook for me." Send that straight off. Now, what's really cool about this is it will lally curate and you have the power of Claudor Chat GPT 5.5 going ahead and building those notebooks for you which is incredible. Then we can go over grab that information save it on our desktop and even vectorize it into Pineco or just like we did with Obsidian have this beautiful thing over here which I open up the graph view so you can see cuz it's very shiny and we like lots of graphs over here. Just use this. Now this is my you know homozy business strategy thing that I can ask questions to. Again I'll put a link on screen for the notebook LM deep dive if you want to double click and learn more about that strategy.
The other one that I absolutely love doing is firecrol. So for example I could say something like this. Hey I want to use my firecrawl integration and go ahead and do some deep research for me on horos five practices for scaling a business past $10,000 a month. Okay do that. Send that one off. Of course, we can connect FC crawl via the connectors on plus. Click on connectors over here. You can see I've got fire crawl installed. And all you literally do is come over, you grab the API key, you can come back over to the connectors. Then what you would do is click on the plus, click on add custom connector, and then right here, you just type in firecraw. And then remote mcp server, just enter in this right here. Where I've got API key, you just enter your firecraw. And then basically what that will then be able to do is use the firecraw agent. And this can save you like 80% of the cost. And it's just way more efficient at getting accurate data for agents.
So what this basically means is we have an archive of every conversation. So every meaningful conversation ends with a wrap-up. That summary decisions, next actions made metadata. The summary lands in the archive. So if I ever say to, hey, what was that thing we discussed about this really important event last January, we've got it. And when we do index it, we have the date and we can set all those different filters in Pine Cone or locally on a computer if we're using Obsidian, which is really cool. That's the exact process we went through. Then we covered the expert knowledge that we've embedded. We've used firecrol to go get some deep research. We can use notebook LM to build beautiful, detailed, impressive notebooks on any topic we want to using the world's strongest AI research bottle, which is freaking incredible. And we can pull that down anytime we want to in our memory system.
So we have the three layers. We have short-term, midterm, and long-term. Level one is who we are. Level two is what we're doing. And level three is everything that's happened before. And that perfect knowledge. Now, your memory system is only as strong as the skills that support it. So, what we need to do next is learn what I call super skills that can make your memory system even more powerful. And we're going to learn that by watching this video right