Diagram: three memories, one agent. An always-on file feeds the prompt, Honcho answers who I am, GBrain answers what we did, and the off-chat files pipeline has no path into the conversation.

What my agent remembers, and where it keeps it

Ted Lasso recommends being a goldfish. It is, he says, the happiest animal alive: it forgets everything in ten seconds and moves on. My agent took that advice. Hermes is a goldfish — every conversation starts from zero, and anything it “knows” about me is either written into the prompt or fetched from somewhere else. And for a while I was one too: it would ask me again about things we had settled a week ago, and I would explain them again, from the beginning. The difference between us is that I could do something about it. So I spent a few weeks giving it a memory. We are goldfish, the agent and I, but only one of us was going to stay that way. This is what I learned about the options, what each of them actually means, and the architecture I ended up with. ...

September 30, 2026 · 8 min · Romit Raj
The LLM cost proxy dashboard: daily token bars and a per-model cost table.

Metering what my Hermes agent spends

My agent, Hermes, talks to me on a Matrix server I run myself. Self-hosting the chat window was a privacy decision before it was anything else, and that setup is a post for another day. What matters here: an agent that chats all day needs a meter. So every LLM call it makes goes through a proxy I wrote — and “wrote” deserves an asterisk, because I’m a lawyer. An LLM helps me code things out; I mostly argue with it until it works. One SQLite file tells me what it spent today. ...

September 20, 2026 · 2 min · Romit Raj