OzBrain - Shared knowledge brain for AI agents and teams
Show HN: OzBrain, a shared brain for knowledge between agents and your team
OzBrain is a hosted knowledge base that serves as a shared brain for AI agents like Claude, ChatGPT, and Cursor. It structures your knowledge into articles that agents can read and write, ensuring every agent works from the same current information. With features like automatic organization, conflict detection, version history, and refactoring, OzBrain eliminates the need to manually copy context between tools. It offers encrypted storage, audit logs, and easy export, and can be connected in under two minutes via MCP connectors.
One shared brain that Claude, ChatGPT, Cursor, and every AI can read and write. It structures what you know so agents read only what they need, and means you never explain yourself twice.
- Sammi
I have a folder called reports, plans, and code-reviews in each repo. I put my md files for agents there, and voila they're in the cloud along with my source code in git. I just talk to my local agent about these files and it finds things using grep and whatever. Done. No mcp or special server needed.
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?
- gavinboston
Do you have a solution for degradation in accuracy when compiling larger amounts of llm-produced text?
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.
- sinuhe69
I think the central question for a such memory system is whether we or the agents can find the relevant information and how to organize these data as changes continues to come in. Would we miss something in the retrieval process? How do we organize the information so they stay actual and correct without piling up the garbage? Of course we can continue to concatenate the data and tag them with version and date, but then we have to face the problem of extracting the relevant information in a short time. If we delegate that problem to a LLM, long context retrieval performance will degrade and the cost will explode.
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.
- rgbrgb
nice :)
> 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.
- jen729w
I'm Johnny.Decimal. [0]
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