Your Dropbox for agent knowledge (it works without you having to "work" it or maintain it.) Every agent you use reads and writes to the same brain, and so do your teammates and theirs. Start a new chat and it can know what you've all already worked on. Your IP, research, sci-fi romance novel or notes are encrypted and I won't train on it. Export it to markdown and leave whenever, because I think you shouldn't have your knowledge locked in anywhere, including OzBrain.
Howzit, I'm Darius or Bubs on the internet.
A long time ago I started my career as an engineer, then moved into CEO roles and over the years lost my own ability to build anything. I was able to get back into code a couple years ago with AI because I know how to build the systems but just don't speak any of the current languages... any ColdFusion homies still around? and in the last 6 months I've gone deep into the frontier of how folks actually use AI and how it can work for real people. I built a semi-autonomous engineering workflow that lets me orchestrate agents to go from a high level feature or business case (sent from my phone at the gym) to shipped code I can usability & human review. I feel very unlocked and it's been super fun.
I was building a voice AI for older folks and I was meatproxy'ing .md files and instructions between Claude on desktop/mobile, Claude Code locally/remote, Codex and Cursor when I wanted an adversarial review of core things... and then I'd improve one of those root instruction/plans and then forget which version was where... so I made some tables in my DB as all my tools already had MCP access to Supabase... and then talking to more than a hundred heavy AI users (vcs, engineers, trainers, teachers, realtors, etc) a vast majority had this problem and didn't want to yolosolo their own solution... 35% of the hundred did tho and all had some different version of .md/git/obsidian/sync. So I rebuilt v2 of my brain, made it more robust, better maintenance to keep it sharp and made it so anybody can sign up and work with their agents and share brains with the people they live or work with.
The plain version: it's your Dropbox for agent knowledge. You set it and forget it, and now you have all your stuff where you want it. Every agent you use reads and writes to the same brain, and so do your teammates and theirs. Start a new chat and it can know everything you've worked on... and anything your collaborators worked on.
It handles conflicts for you. Stage/promote and there's automatic resolution for writes so a bunch of agents can work at the same time (decisions are always logged so you know who did what and why). New thinking doesn't erase the old, it deprecates it and links to the newest thinking. Your brain is encrypted so your IP, research, sci-fi romance novel or notes are private and I never train on it. You can export the whole thing to markdown whenever you want and leave because I think you shouldn't have your knowledge locked in anywhere, including OzBrain... but my goal is to deliver such obvious value you're happy to let me take care of it for you.
I'm not trying to sell the smart engineers who don't get why they wouldn't just use a git repo for this. There are hundreds of millions of people who run their work through AI and need a shared knowledge system, and I'm building for them... and some of those engineers who just can't be bothered to maintain another thing. ;)
It's still early: the maintenance loop is in alpha, but I used OzBrain to build OzBrain... I've used it to create nearly 1k articles that document what I'm building, why, who for, how and everything else I learn along the way.
I don't need to change the way you work... since we all find our own little grooves, the best way to see how OzBrain can help you do more with agents is to grab the prompt on the homepage and hand it to Claude / ChatGPT and ask your own agent.
Grab the "Ask your agent prompt" from OzBrain.com
And if you've built your own brain, I'd love to hear how you did it.
Cheers. Happy knowledge sharing.
@bubsexcited to see this one live! I've been on the beta for a few weeks, it's one of those immediately useful/straight into my daily workflow tools like Wispr flow/granola/claude routines. set up was a prompt or two, and I just added in a line to my common skills to update ozbrain when the skill runs.
I've found it super useful for product analytics and GTM insights, even kicking off a new feature. Feels like the glue between a lot of systems we run on nitrosend, I don't think I've been back to the UI since I set it up but I use it all the time (from my agent). Very cool
Panic Free Symptom Checker
Nitrosend
@bubsexcited to see this one live! I've been on the beta for a few weeks, it's one of those immediately useful/straight into my daily workflow tools like Wispr flow/granola/claude routines. set up was a prompt or two, and I just added in a line to my common skills to update ozbrain when the skill runs.
I've found it super useful for product analytics and GTM insights, even kicking off a new feature. Feels like the glue between a lot of systems we run on nitrosend, I don't think I've been back to the UI since I set it up but I use it all the time (from my agent). Very cool