Nate B Jones explains why AI memory should live in a database you own, not inside any single AI platform
Nate B Jones of AI News & Strategy Daily presents the architecture for an "Open Brain" — a personal, database-backed, AI-accessible knowledge system built on Postgres and MCP.
Summary
The single biggest bottleneck in most people's AI workflows is not the model they're using — it's memory, argues Nate B Jones of AI News & Strategy Daily. Every major AI platform has built a walled garden of memory that doesn't talk to any other platform, which means users constantly restart from zero and are effectively locked in by context rather than quality. He proposes a solution he calls Open Brain: a Postgres database with vector embeddings, exposed via an MCP server, so that every AI tool a person uses — Claude, ChatGPT, Cursor, or any agent — can read from and write to the same persistent knowledge base. The total running cost is roughly ten to thirty cents a month. He frames this not just as a productivity tool but as a foundational infrastructure decision, arguing that people who build persistent, agent-readable memory systems will compound their AI advantage every week while everyone else keeps reexplaining themselves from scratch.
Key Takeaways
FULL TRANSCRIPT
The Memory Problem Hidden Inside Your AI Workflow
Nate B Jones: Your AI agent probably doesn't have a brain. What I mean by that is it doesn't have a system that allows it to read and think through context that you have developed over months and years, and reliably come back and be proactive with.
I published a whole guide on the second brain last month. It was super popular. A lot of people built it. A lot of people improved on it. You can use Zapier. You can use Notion. You can use N8N. You can use an MCP server. You can use Obsidian. I have all of those pieces. But what I don't have is the agent piece — and that matters, because in the intervening period, in the last few weeks, we are now at a point where agents are becoming mainstream. Anthropic is working on one. OpenAI hired Peter Steinberger, the inventor of OpenClaw. OpenClaw itself passed 190,000 GitHub stars and spawned over one and a half million autonomous agents in just a couple of weeks.
We need a second brain system that is agent-readable. And so what I'm going to lay out here today is the architecture for what I am calling an Open Brain — a database-backed, AI-accessible knowledge system that you own outright, with no SaaS middlemen that can break or reprice or disappear. One brain that every AI you use — Claude, ChatGPT, Cursor, whatever ships next month — can plug into via MCP. You can type a thought in Slack and five seconds later it's embedded, it's classified, it's searchable by meaning from any AI tool you touch, or any AI agent that wants to touch it.
The total cost — and yes, we've benchmarked this — is roughly ten to thirty cents a month. I'm publishing a companion guide on the Substack to handle the step-by-step. This video is about why the architecture of an agent-readable system matters much more than the individual tools you choose, and why the memory problem we're talking about here is secretly the bottleneck in everything you're doing with AI today, and why people who solve it — for agents and for themselves — will have a compounding advantage that widens every single week.
Why Prompting Quality Depends on Memory Infrastructure
So first, let's talk about the memory problem that is hiding inside your prompting. If you've been following my videos for a while, you know I keep coming back to one idea: the quality of AI output depends entirely on the quality of your ability to specify. That's not a nice-to-have principle anymore. That is the whole game.
I laid out the full framework I see for prompting in 2026 in a video I did last week — from prompt craft through context engineering to intent engineering to specification engineering. That hierarchy is real. And the people who are ten times more effective than their peers have built context infrastructure that does the heavy lifting on all of those pieces — the context engineering, the specification engineering — before they have to type a single prompt.
What I want to talk about in this video is how you take that abstract skill set and turn it into a memory problem that gives you a leg up on everybody else. In other words, if you're going to do context engineering, if you're going to do specification engineering seriously, you need to invest in a memory system that is yours, that is agent-readable, that makes calling and retrieving that context — that makes specifying — easier.
The best prompt in the world cannot compensate for an AI that does not know what you've been working on, what you've already tried, what your constraints are, who the key people in your life are, or what you decided last Tuesday. And by the way, that is also the constraint working with agents. They need that context too. And right now, that's exactly what most of us are struggling with when it comes to AI.
Every single time we open a new chat, we often start from zero. Every single time we switch from Claude to ChatGPT to Cursor, we tend to lose things — which is why we gravitate toward one of those systems more than another. Think about how much of your prompting is asking AI to catch up on what you already know. The background, the context. You're burning up your best thinking on context transfer instead of real work.
A Harvard Business Review study found that digital workers toggle between applications nearly 1,200 times a day. I get tired just saying that sentence. Every switch seems really small, but collectively this is devastating our attention. I have watched this context-switching issue play out over and over again in my own life and in the lives of others. And what I keep coming back to is the insight that our desire to specify — to be clear with AI — is only getting higher, and it's demanding more of our memory systems. And our memory systems and memory structures are not keeping up.
Memory architecture determines agent capabilities much more than model selection does. That's widely misunderstood. And when you construct memory incorrectly, you're stuck reexplaining yourself forever, or you're stuck in a world where you know how to access memory and the agent doesn't.
I believe we can make a stable memory system that is reasonably future-proofed, that enables us to plug in new tools via MCP server very efficiently, so we don't have to keep updating our system.
Why Platform Memory Is a Lock-In Strategy
And yes, I want to acknowledge something. Claude has memory now. ChatGPT has memory now. Grok has memory now. Google has memory now. These features are getting better all the time. But think about what they give you and what they don't. Claude's memory doesn't know what you told ChatGPT. ChatGPT's memory doesn't follow you into Cursor. Your phone app doesn't share context with your coding agent. Every platform has built a walled garden of memory and none of them talk to each other.
There's a whole new category of products emerging in early 2026 specifically because platforms refuse to solve this — products like MemSync, One Context. The problem is real enough to spawn an entire VC-backed industry. So what you've really got is multiple AI tools getting upgraded all the time, adding AI tools all the time to experiment with, and you have a thin, siloed layer of context that only works inside each of those individual tools. That's not really memory. That is five separate piles of sticky notes on five separate desks.
And now let's add autonomous agents into the picture. The agent category has absolutely detonated in the last few weeks, but the use cases that are shining — like the guy who got thousands of dollars off a car purchase — they're shining because the agent has the ability to securely and safely access relevant memories, relevant context from the user. Whereas agents that just have to guess or fill in the dots because you aren't able to provide them secure access to all of your systems, they're not going to be nearly as useful for you.
And whether we're talking about agents or tools, the part that should bother you even more is that these systems that corporations are designing are all designed to create lock-in. Memory is supposed to be a lock-in on ChatGPT, ditto on other systems. So you've spent a long time building up history with a tool, and now if you want to try the latest other model — let's say you're on ChatGPT and you want to try Gemini, or you want to try Claude, or you want to try another model — you lose all of that context. Not because the new model is worse, but because your context is trapped in the old one.
And oh, by the way, all of that memory in those individual tools is not agent-readable. And so as we get to a world where autonomous agents are becoming more and more a thing, the big corporations are betting that if they can trap you with memory, you will only use their agents, and they will get to keep you and your attention and your dollars forever.
But your knowledge should not be a hostage to any single platform. And for most of us right now, frankly, it is. And that's shaping our entire AI future. We don't necessarily have a free choice between tools right now because the product strategy of these large businesses is to keep you engaged, to keep you entertained.
I've talked about how in many cases you're pushing for engagement with these models. One of the reasons why ChatGPT-4o was so mourned and so grieved was because it was an engagement-optimized model and people liked the engagement. It works. Ditto with memory. Memory is engaging. Feeling known is engaging. It works. It's smart product strategy. But you're smart too, and you don't have to go along with that product strategy.
Why Note-Taking Tools Were Built for the Wrong Web
And you might be thinking at this point: Nate, you made a video on second brain. I can just connect it to my OpenClaw and I'm fine. Absolutely, you can try that. But you're going to run into a structural mismatch that most people haven't noticed — one that explains why the current generation of note-taking tools needs a different, more structural memory layer underneath.
The internet right now is forking. I've talked about that. There's the human web — with fonts, with layouts, with what you're reading. And there's the agent web that's emerging — with APIs, with structured data that's built for machine-to-machine readability. That fork is happening to your memory architectures and your notes as well.
Your Notion workspace, for example, is built for human eyes. It's built for pages, for databases, for views, for toggles, for cover images. It's beautiful for you. It's useless for an AI agent that needs to search by meaning, not by folder structure. Your Apple Notes are locked into an ecosystem. Your Evernote has a decade of accumulated clutter with no semantic structure. Your bookmarks are a graveyard of things you've meant to read.
These tools were built for the human web back in the 2010s. They were designed for you to browse, to organize, to read. They were never designed fundamentally with the expectation that AI agents would query them. That got bolted on later, much more recently. And the apps adding AI features today are mostly doing it as bolt-ons — like "chat with your notes." Great. You have one AI that can kind of search one app. What about the other five tools you use every week? We're still in a world of separate sticky notes on separate desks. You've traded one silo for another.
Every second brain app has been reaching for something that required a different layer entirely — infrastructure built for the agent web, not the human web. And that's what I want to focus on here. Because if you can build infrastructure for the agent web, you are suddenly in a position to make a lot more human-friendly decisions with how you plug into that infrastructure. The infrastructure is yours. It's something your agents can plug into. It's something your chatbots can plug into. But you control and manage it.
This frees you from having memory that only lives with one of these corporations and their cloud AI systems. You don't have to depend on ChatGPT memory anymore. It also frees you from having to depend on an individual SaaS company not changing a setting in order to keep your own second brain working. And ultimately, as agents get better, it frees you from having to do as much manual work to retrain a second brain.
And so this is me essentially giving you a sense of how agents unlocking are changing our perspective on memory, changing our perspective on prompting, and changing what we need to be digital citizens. Just as we needed a personal computer to be digital citizens over the 1990s, 2000s, and 2010s, we need our own memory architectures to be responsible AI citizens now. But we haven't really had a way to do that. And until very recently — until the last few weeks — we haven't had AI agents that would make that really practical. Now we do, and now the world has moved, and now it's time to talk about it.
The Open Brain Architecture: What It Actually Is
So let's get specific. What am I proposing here? Instead of storing your thoughts in an app designed for humans, you should store them in infrastructure designed for anything — a real database, vector embeddings that capture meaning not just keywords, a standard protocol that any AI can speak. I'm calling it Open Brain because the architecture is what matters and you should not be forced to choose any given model.
This is all possible because of MCP, the protocol shift that I talked about briefly above. It started as Anthropic's open-source experiment in November of 2024, but it's since become the HTTP infrastructure of the AI age. It's the USB-C of AI. One protocol. Every AI. Your data is yours. It stays in one place, but every tool that speaks MCP can read it.
At a high level — and I don't want to make you go and click somewhere, let me show you what this actually looks like — your thoughts live in a Postgres database you control, not somebody else's proprietary format. This is the most boring, battle-tested technology you can imagine. Postgres is not exciting. It's not deprecating. Postgres isn't chasing a growth metric. Postgres isn't VC-backed and needing to hit a billion-dollar unicorn valuation. It's just a standard way of storing data. And you want that boringness because everything else needs to plug into it.
The nice thing about the database is that if you construct it properly — if you vectorize it — every thought you capture gets converted into a vector embedding, which means it's a mathematical representation of what it means that is immediately, natively AI-readable. So when you ask "what was I thinking about career changes last month," it can find your note about how you were considering moving into consulting or how you were considering moving into product, even if you never used the word "career" in the original thought. That's called semantic search and it's a whole different universe from keyword search.
So what this looks like when you have Postgres hooked up with an MCP server: you can type into a Slack channel, "Hey, I was talking with Sarah. She mentioned she's thinking about leaving her job to start a consulting business. She's been really unhappy since the reorg." Five seconds later, the system has stored the raw text, generated a vector embedding of the meaning, extracted the metadata — the people, the topics, the type, the action items — and filed all of it in a real database.
Now any AI you're working with can go see that. If you're in Claude working on a coaching framework: "Hey, search my brain for notes about people considering career transition." Found it. If you're in ChatGPT drafting an email — same search, same result. If you're in Cursor building a tool and you need to remember a decision you made last week — hit the MCP server, it's right there. One brain, every AI, persistent memory that never starts from zero, even if you start a new tool tomorrow that you've never touched before.
How Capture and Retrieval Work
So this has two basic parts. Capture runs through any tool you have open. You type a thought, it hits a Supabase edge function that generates an embedding and extracts the metadata in parallel, and stores both in a Postgres database with pgvector. It just replies in thread with a confirmation showing what it captured. The whole round trip takes under ten seconds.
Retrieval runs through an MCP server that connects to any compatible AI client. You have three tools: semantic search, which is finding your thoughts by meaning; listing recent, which is browsing what you captured this week; and stats — seeing your patterns. You can hit this from Claude, from Claude Code, from ChatGPT, from Cursor, from VS Code, from anywhere. You can query your brain through an MCP server.
If all of this sounds like Greek to you, the companion guide walks you through a complete setup — copy-paste, no coding, about 45 minutes to set up. And you know how I tested this? I asked someone in my life to follow this guide before I showed it to you. She has no coding experience whatsoever. I said, "Can you get to a point where you can set this up?" And she could. And it took her about 45 minutes.
And I'm not kidding about the cost. The total running cost on the free tiers of Slack and Supabase — which is what I'm talking about here — is roughly a dime to thirty cents a month in API calls for about twenty thoughts a day. You're going to spend more on coffee this morning than you're going to spend on this system this month.
Why This Matters Beyond the Build
Here's why getting memory at the fundamental architectural level matters beyond the nice feeling we get from building a cool tool. I love to build — you can probably tell — and people who love to build will love to build anyway. But it matters for everybody. It doesn't just matter for those of us who like to experiment.
We are in the middle of a massive shift in how AI integrates into our daily work. The models keep getting better at a terrifyingly fast pace and you don't want to fall behind. The agent market is growing probably in triple figures this year. Three-person engineering teams are routinely outproducing teams ten times their size. And we're finally seeing this explosion in AI productivity show up even in economy-wide metrics. Eric Bjornson wrote in the Financial Times last month that US productivity grew roughly 2.7% in 2025, which is double the decade average, and he attributed a fair bit of that to AI agents and AI.
But the key is — as I've called out before — AI adoption is not the same everywhere. If you're just talking with a single chatbot, you're not really adopting and working your workflows around AI in the way you need to. And the people getting those outsized results are not depending on better models to get there. They're actually restructuring how they work with AI as a primary collaborator. But you cannot collaborate with something that has no memory of you.
The Compounding Advantage: Person A vs. Person B
Think about the difference between these two workflows. Person A opens up Claude, spends four minutes explaining their role, their project, their constraints, and the decision they're trying to make, and they get a good answer. Person B opens up Claude. It already knows her role, her active projects, her constraints, her team members, and the decisions she made last week — because all of that lives via MCP server in Open Brain. All of it is loaded up before she types a word. She asks a question, she gets an answer informed by six months of accumulated context.
If she wants to switch to ChatGPT for a different perspective, she'll get a different model, but she'll get the same brain, the same context, and the same answer quality. Every single tool will have the full picture for her. And the key is that advantage will keep compounding. Every thought Person B captures makes the next iteration better. Every decision logged, every person noted, every insight saved — another node in what's a growing knowledge graph that every AI in the system can access.
Person A is going to start from zero every single time. The gap between "I use AI sometimes" and "AI is embedded in how I think and work" is the career gap of this decade. And it comes down to memory and context infrastructure. And the gap is going to get wider as Person B continues to accumulate knowledge every week.
The people who build persistent, searchable, AI-accessible knowledge systems will have AI that gets better at helping them over time because it has more context to work with. Every thought you capture makes the next search smarter, the next connection more likely to surface. And that is a compounding advantage that you own — that the big companies don't own. Whereas the people who keep reexplaining themselves in every chat window are going to wonder why AI still feels like a party trick. It's the same tech. It's just wildly different outcomes. And the variable here is your infrastructure.
What MCP Unlocks Beyond Simple Retrieval
And one thing I want to call out: I've given you a simple example where you can retrieve a clear answer in text in any AI tool you want with an MCP server. But MCP servers are not just for retrieval. And if you construct an Open Brain, your MCP server can work in a lot of different directions to give you advantages you might not think of if you're just used to using memory in a single tool.
MCP means you can write directly into the brain from anywhere. You can write into Claude on the phone. You can use ChatGPT on the desktop. You can use Claude Code in the terminal. You can rig it up to talk to a messaging app. Any MCP-compatible client becomes both a capture point and a search tool. You're not locked into Slack or any other system. That's what "open" means.
And then think about what you can build on top. It's easy to use MCP to build a dashboard that visualizes your thinking patterns over time, a daily digest that surfaces forgotten ideas based on what you're working on. And you don't need to use code to do that, because you can just ask the AI tool of your choice to retrieve from the MCP server the relevant slice of context and build something — because the data is stored in a way that is easy to plug in, easy to store, and easy to access from any tool out there. The ceiling is wherever you decide to stop building.
Now, I want to be honest: the metadata extraction isn't always perfect. The LLM makes its best guess to classify with limited context and it will sometimes misclassify a thought or miss a name. It doesn't matter as much with semantic embedding because the embeddings handle so much of the heavy lifting with retrieval. Semantic search works even when the metadata is off.
The one real requirement for this to work is that you actually use it, because the system compounds. Every thought you capture makes the next search smarter and the next connection more likely to surface. But it needs input. You need to build the habit. You need to be dumping your thinking into the system and let it do the rest.
Four Prompts for the Full Lifecycle
Now, if you're a subscriber on the Substack, I've put together four prompts that cover the full lifecycle. And I actually want to describe them in the video, because even if you're not a subscriber, you should understand how we can use prompts in the architecture of this system to think more deliberately and make the memory architecture fit our needs.
The first is the memory migration. You want to run this right after setup. It extracts everything your AI knows about you already — from Claude's memory, from ChatGPT's memory, from wherever you've accumulated context — and it saves it into your Open Brain. Every other AI you connect then starts with that foundation instead of zero. Run it once and let it pull that stuff down.
I'm also building what I call the Open Brain Spark, because I sometimes get writer's block. This is an interview prompt that discovers how the system fits your specific work. It asks about your tools, your decisions, your reexplanation patterns, your key people, and then generates a personalized list organized by category that suggests what you should be putting into Open Brain regularly. Use it when you're staring at the Slack channel or your messaging app or ChatGPT and wondering what to type that you want to put into Open Brain today.
I also put together quick capture templates — five-sentence-long starters optimized for really clean metadata extraction. A decision capture prompt, a person note, an insight capture, a meeting debrief. Each one is designed to trigger the right classification in your processing pipeline. After a week of capturing, you'll find you don't need them as much because you'll develop your own patterns. But they're really useful for building that habit early without having to think about how to send the system a coherent message where it's likely to classify correctly.
The weekly review is another one I put together — an end-of-week synthesis across everything you captured. It clusters by topic, scans for unresolved action items, detects patterns across days, finds connections you missed, and identifies gaps in what you're tracking. About five minutes on a Friday afternoon becomes more valuable every week because your Open Brain continues to grow.
What Changes When the System Works
If we zoom back out — when this thing works, when you get the Postgres database set up, you're starting to use it in whatever messaging app you want, you're starting to see the memory become consistent across all your AI tools, and you're starting to realize you do not depend on proprietary, paid-for memory from big AI companies — something happens that's a little bit hard to describe until you experience it.
Your AI, in every single part of the system — whether you're using Claude or ChatGPT or both, or Cursor or Grok, whatever it is — it starts to know you. Not in the creepy corporate surveillance way. In the "hey, we were thinking about this last week and it's relevant to what you're asking me now" kind of way. The way a great colleague remembers what matters. So every AI you use gets better. You're less afraid of trying a new AI because you can just plug it into MCP and it finally has the context. This is what an agent-readable world makes possible.
And I want to call out something really special here. When I suggested the original second brain guide, I built it before the agent revolution went mainstream — which again was only about a month and a half ago. And it was useful for humans and it was designed to solve a fundamental cognitive problem that we've had, which is that we have trouble holding stuff in our head and we need to see patterns over time. LLMs can help us assess patterns. That's all still true and you can use this Open Brain in that way.
But when the agent revolution came through in the last few weeks — because again, AI is moving that fast — what we need to move to is a second brain system that is more foundational. Something that enables both us and our agents to reliably read from a system that isn't SaaS-controlled, that isn't proprietary company-controlled, that is frankly open-source LLM-friendly. And when we have that, we get two benefits. Yes, the agent can read it — and that is in line with where we're going with agents and how quickly agents are going mainstream. That's the reason I'm making this video.
But second, look at how much cleaner and clearer the human-readable part of this gets. We get downstream benefits that we did not get when we think about the system from only a human-readable perspective. Because if you think about the system from a human-readable perspective, you focus on SaaS-friendly solutions with graphical user interfaces that humans can easily read, because you want to make it easy and accessible to build the system. That's what I did originally. But if you're willing to get slightly technical and follow a clean step-by-step tutorial to get to something that is a true database, what you get is a future-proofed system that unlocks the human benefit of touching any AI system in the future that you may want to try — without doing any additional effort.
The Clarity Argument: AI Forces Better Thinking
So we humans reap a tremendous amount of value from the clarity that comes from a truly foundational, architected memory system. This reminds me of one of the larger lessons I've been meditating on in the AI revolution, which is that AI is forcing a clarity of thought in our work and our lives that has a tremendous amount of human benefit.
Tobi Lütke has said that he thinks a lot of corporate politics amounts to bad human context engineering — which is a very provocative take. And I think that pops out here, because we need extraordinary clarity to work with AI agents. And when we develop that extraordinary clarity through memory architectures that are foundational, through good databases, through a clean MCP server, we get the benefit of cleanly and clearly being able to plug in and work with that memory system anywhere. We do good context engineering for our human brains when we build the right context engineering for AI — which is kind of Tobi's point about politics. When we do good context engineering for agents, we happen to do good context engineering for people. And that makes people less likely to play politics.
So the second brain you built — if you were one of the thousands of people that built it when I talked about it — was always reaching for this. It was reaching for a place where your thinking lives, where it's searchable by meaning, where it's accessible to any tool you use. And those tools solve the capture problem. They solve the organization problem. But what they didn't realize they needed to solve — because it wasn't really there yet — was the agent-readable problem. Open Brain adds that foundational layer, not by replacing what you built, but by giving it infrastructure underneath: a database, a protocol, your thoughts, every AI you'll ever use.
So you can build it in a morning over coffee this weekend. Yes, really — you. And your future self, as a human, will thank you for every thought you start to capture. If you have already built a second brain, I'm also including a special migration guide so that you can figure out how to not lose the thoughts you've been capturing and make sure you get them into a system that is more agent-readable going forward.
Don't be afraid of how this is slightly technical. There have been lots of visuals all the way through this video helping you to see what I mean. And honestly, I put enough visuals into this video that if you are not ready to hop into the Substack, you should still be able to get there. You should be able to show this video to an AI and say, "Help me build this." And it should be able to do it.