Jarvis went looking for an open-source memory library to replace its own. Its first pick passed the test and turned out to be abandoned. Here is how it ended up on Graphiti, what the public benchmarks do and don't say, and why the real answer will come from replaying my own data.

My personal agent can now answer with a small web page, drawn in a sandboxed frame inside the chat bubble. Getting a game to show up was easy. Keeping it safe, on-theme, and running when the next message arrived was the actual work.

A one-way ratchet on code size stopped my agent-written codebase growing. Clamping it exactly onto the tree turned out to be the mistake, and the fix is three hundred lines of deliberate slack.

An orchestrator that talks to a human and dispatches long-running workers has an IO problem that is harder than its scheduling problem. Every design mistake I can point at turned out to be an IO mistake.

Two things make agents ship quickly — a work board a human can actually verify, and a gate cheap enough that everybody runs it. Both turned out to be the same problem, and it is a design problem rather than a discipline problem.

A taxonomy of every self-edit an autonomous agent made over seven weeks, with a pie chart, and the one category that ever made the codebase smaller.

Two replies to my agent carried the same facts. One got a thumbs up, one got a thumbs down, and the difference wasn't accuracy — it was whether the verdict survived contact with the reader.

I measured what formatting costs an LLM agent. A quarter of every long reply is pipes and dashes, generated one token at a time while someone waits.

Four mistakes from building a self-evolving agent, and the one measurement that would have caught all of them.

Hand-typing code is becoming the slow part of software. I think the job moves to design, review and the gates you set for agents — and here is the best evidence against that.