So last July I started building a custom Next.js app to run an AI agent called Bobo to help me manage my advisory practice. It worked pretty well... except for one thing that kept driving me crazy.. every new session i would start Bobo would wake up confused with what is actually relevant to the conversation i want to have with it, now. No memory of what we talked about yesterday, what deals were in the pipeline, what commitments were made. I'd spend the first 5 minutes of every session re-explaining everything or copy pasting stuff. I kept trying different approaches and eventually landed on modelling the memory around a literal brain.
Three layers daily notes as raw memory, a rolling synthesis as working memory (I called it the hippocampus), and permanent memory for things that stuck around long enough to matter. It actually worked. Bobo started waking up knowing what was going on.
Every time an AI agent starts a new session, it wakes up blank. No memory of yesterday's work, open threads, or promises.
Hippocampus synthesises a rolling briefing from your agent's daily notes and injects it into every session, automatically, zero config.
