A lot of the “knowledge” ie research, analysis, reasoning will be done by agents as the primary user. Our current notes tools & tasks management systems were built for humans… I don’t care what the 17th thing on my bug backlog is. I want to conduct agents that can execute for me and do great work.
What I built OzBrain to do: + Create a central place for agent reasoned knowledge to live + Be agnostic about what apps/agents connect to it + Capture everything and track it so I can audit it + Enable teams, collaborators or partners to share brains + Handle conflicts so many agents in the same article doesn’t blow up + Refactor knowledge into more token friendly chunks and map the index well + Close the knowledge loop so new thinking supersedes old thinking across the corpus. Don’t erase, depreciate and link + Keep user data safe and secure ++ Be easy enough to use that you don’t have to have any technical knowledge
Some among us will always build their own custom solutions, but there are millions of tech professionals and small business owners that will use agents heavily and need a solution. So I’m trying to build that.
Isn’t this like gBrain? Yes, similar. I think it’s like AWS vs Vercel. AWS is very powerful, configurable, and useful if you’re technical and want to invest the time into really fine tuning your system… but if you just want your web deploy/hosting to just work and be easy to deal with you use Vercel.
// WHY I MADE IT
I’ve been enjoying getting back to my technical roots, as I lost my coding skills more than a decade ago, but with AI I can focus on the system and the product in partnership with agent coding workflows.
I recently built a Voice AI for older people. To build it I created an agentic engineering workflow (feel free to rip that up as I’m always looking to improve systems: https://ozbrain.com/resources/eng-flow) My approach with coding agents is trust but verify, and I’m trying to replace the parts where a human would review with an adversarial or specialized agent who would give a better answer/review.
I have workflows that will go high level task to shipped PR running in Claude cloud sessions. I use Claude Code locally and Cursor when I want a tighter loop on doing visual work like UI or layout. And Codex to either load balance usage for TokenThriffting or when I want a different llm to think thru something.
It was a pain in the ass passing .md files around and keep track of which version was the most recent, so I built a hosted .md storage right in Supabase and any of my agents already have Supabase access. This let me build a solid, scalable, secure voice AI from my phone at the gym. All my agents have access to our knowledge, can write to it, update and refer to it as we build and improve the product and the systems we use.
Out of 75 founder friends I asked about how they manage shared knowledge, 26 built their own custom knowledge systems… Obsidian vaults with 7k files synced through a VPS, markdown repos behind their own MCP servers, cron jobs stitching Supabase to a skills file… each a different Frankenstein they have to maintain. 32 said they felt the pain of moving static files around but didn’t have any solution for it.
So I rebuilt my brain better and used it to build it.
// HOW YOU CAN HELP
Would love to have you try it out. The maintenance loop is still in alpha so not running it on customer data yet.
If you built your own brain I’d love to hear how you did it. What criteria was most important for you in its design & function.
If you are tired of shuffling .md files around I’d love to have you try out OzBrain and to give feedback, just ask your agent to put it in the shared bugs & features brain!
Cheers! Bubs.co
My agent (Hermes) responds to a made-up command "vaultize this doc/link/text, etc" to add new .md files in the right format in the right place. The agent does a pretty good job of maintaining the index.md file, cross-links, etc.
A Quartz website builder creates a static site on my server, each MD file is a web page, and rebuilds when a new file is added [2]. This setup gives me a useful knowledge base with a great UX - across all the devices on my Tailnet, no need to run Obsidian Sync, or Syncthing.
This system is simple and works well, but i think it could maybe benefit from a memory system like Honcho to make it more effective as it scales.
[1] https://cloud.google.com/blog/products/data-analytics/how-th...
I've been pitched products like ozbrain before, but I've failed to see the need over what I already have. Seems like more complication for no gain to me.
Am I missing something?
I am also building LLM knowledge/memory systems and I've been surprised how bad LLMs are, even SOTA models, at summarizing non-trivial input batches of text. They get things wrong, distort the underlying meaning or data, etc.
I run https://smalldocs.org, which focuses on making Markdown a highly expressive space for agents (think slides, spreadsheets, charts, mermaid diagrams, etc.). I have built a local library which lives in the browser but reflects your local file system - explainer here: https://smalldocs.org/connect?return=%2Flibrary, demo here: https://smalldocs.org/library?demo=1. Which is pretty useful when you want to find local Markdown files.
However I am just about to introduce very similar functionality to yours - a cloud + agent access. Right now I don't know if this will actually be useful, but I think it will likely be something I can charge for. I have a few hundred developers that use SmallDocs on a weekly basis (https://smalldocs.org/analytics), but right now it's just a free local-first tool.
Code available here: https://github.com/espressoplease/smalldocs
That is the reason why we condense the information in the first place. Forgetting + Synthesizing are the necessary parts of learning and basically with memory + smart retrieval we want to build a learning system.
This will be the big challenge with this. Storing/Retrieving works fine across hundreds of articles... I have more than 500 right now just from OzBrain and a bit of the thing I was building before. When it becomes thousands with dozens being added all the time, the maintenance will become more of a necessity.
I lean a little bit towards store everything because the system's abilities are changing so fast right now, that having our previous thinking or reasoning is useful in being able to improve or correct current assumptions based on previous data.
I wish the author had made a mental image like “OzBrain is a Zettelkasten system built with AI background maintenance” then things will become much easier for the readers to understand.
> love to hear how you did it
this is ours we built for Hedgy https://setoku.com
our approach was to build a data lake that sucks company data into clickhouse and staple that to a knowledge store. this way the brain has a stream of live facts and builds knowledge around it. we gave up on trying to make the knowledge store human-readable -- i totally think there could be something there, but for now we just care about enhancing the agent you're using. it makes my claude code very good at debugging and gives everyone a way to vibecode dashboards and small internal tools with real data.
i also run a personal instance for my wife and I that sucks in monarch money and gmail. mostly use it to chat through big money moves.
I'm assuming that the content you put in is all agent driven. Source files (ie, a transcript, a data log, stuff that shouldn't eery change) get recorded but the articles are some kind of agent reasoning on top of it. I don't have any interface to edit an article. Your agent does it.
And yeah I agree about not building for human consumption. The agents create and consume vasly more data than we can.
I don't do any ingestion, I figure out can automate that in a routine or a zap or whatever you want.
Would you consider this a different type product/benefit than all the "memory" things we have seen popping up everywhere?. Is it different just because it lives in the cloud? To me it feels like a different thing than memory.
This feels like an important layer of the emerging agent stack, and I think this Show HN will be useful to a lot of people working through exactly that problem.
I use an Obsidian vault and my system. "It's at 23.16", I tell Claude. From that it can instantly find my notes and files.
No extra software needed. Just some basic structure. Claude loves it. [1]
Oh yeah, and to keep conversation context contained so you can /resume and so on, just
$ cd 23.16
$ claude
Are you seeing engineers use it or more every day people getting the hang of it to?
Good luck with the showing!
That also gives me a reason to pause, tho; the pitch in general is as solid as it can be on a site with markdown turned off (why, lord, why), but as a format minutiae megafan, I was left a little dissapointed. Where do you/OzBrain stand on Markdown formats? Could I use Sphinx with this, in rST and/or native MyST? Can it generate plain PDFs, fancy PDFs, or even animated static sites? etc. etc. etc. Not trying to gotcha, just curious to hear your thoughts & dreams on the topic!
It seems like some subculture(s) of SWE/SV/YC/AI has landed on obsidian-ish markdown with lots of wikilinks as the presumed default, which makes sense. So I'm assuming it's the same here. But also, your 'OzBrain vs. Obsidian' page does describe one difference as 'Markdown export anytime' vs. 'Markdown on disk' -- presumably that's just a hedge about hosting paradigm rather than a comment on the persistent format?
P.S. You're likely aware but there's at least one other company using Oz -- Warp's coding agent. Have you considered renaming this to something unimpeachable like DeepReasoningBrain? ;)
P.P.S. Holy hell your `eng-flow` thing is incredible. Maybe I'm behind the times, but... I mean, has anyone else processed how close we are to Minority Report and Iron Man?!
P.P.P.S. Is any part of that/this OS?
OzBrain is text only, and basic markdown formatting (OKF). No fancy PDFS, etc. BUT that is what your agent is for. If you want to generate a fancy PDF, have an agent reference the relevant articles and generate what you want. I've considered a lot of additional services like automatic ingestion, ie every call transcript auto-ingested as a source article in the brain... but you can do that with routines or Zapier. My focus is on the infra of the data getting to and from your agents.
I think Karpathy's llm-wiki was a boost to the wiki-markdown club, and it makes a ton of sense why a technical person would adopt that. They're already veru comfortable with github and moving files with terminal commands. They're not my target audience right now, but maybe when we have more robust brain maintenance they'll decide it's jsut easier to use OzBrain and not maintain their own thing.
P.S. In true move fast break things mode... I spent a good 15min working on the name. :) It works for now and if it really works well for people and they love it, the name won't matter so much.
P.P.S. Thanks, it's either genius or incredibly stupid... hard to know these days as stuff moves so quickly and your AI tells you you're so smart. It's what I HAD to build, because I don't speak any of the current languages. I lost my coding skills long ago, so at a point where it might make sense for a smart engineer to review or approve something... I needed to insert an agent that actually knows what it's talking about and understands how to make a good decision. That thing is constantly improving or breaking... I tried to automate one more step a few days ago and have been paying the price and bug fixing my thing that builds things, instead of just BUILDING THE THINGS! ugh.
P.P.P.S. I mean I used OzBrain to build OzBrain and make that eng flow work. If you think something in there would be useful, I'd just point an agent at it that is connected to your whole workspace/flow and ask it what is useful/dumb.
*Bonus point. Because my whole brain is in OzBrain and it knows what I'm building, why, how... I can take a talk transcript like Garry's from Startup School and just ask an agent "Save this transcript in the brain as a source and then review it and show me where this validates or invalidates some of my thinking. And what else would be interesting for me to consider in my broader work."