Thoughts on AI agents, persistent memory, and knowledge work.
Look at your phone's home screen. Really look at it. A weather app. A calendar. Gmail. Some app your grill manufacturer made. Here's the thing: you don't need any of it anymore.
Nate Jones built a self-hosted AI knowledge base. It works great. It's also 45 minutes of setup you now have to maintain. Here's the hosted version.
It's alive! Brains is a persistent knowledge base that connects to your AI. Whatever you're working on, whatever you've figured out, whatever your AI should already know: it's there the next time you open a chat.
I'm building an AI memory tool using AI. The same AI that uses the tool to remember my project helps me build it. It took about session 47 to notice what was happening.
A few weeks ago I spent some real time thinking about whether I should keep building Brains. Not the motivational kind of thinking. The uncomfortable kind.
I talk to myself a lot. In the truck, in the garage with greasy hands, right before I fall asleep. Here's how a two-minute voice memo turned into a workflow that actually works.
Every time you start a new chat with an AI assistant, it forgets everything. Here's why that's a fundamental problem, and how persistent memory changes the game.
Every major AI platform is quietly adding memory features. That sounds like good news. It isn't. At least not the way they're doing it.