Design notes from building an autonomous personal agent: ontologies against bigger context windows, memory that survives, and what an agent may do unasked.
More context makes an agent better informed and no more reliable. Structure is what lets it check a claim, trace a fact and notice it is contradicting itself.
An agent that starts every conversation from zero is a very good stranger. What has to persist, what should decay, and what must never be written down at all.
Connecting a model to your inbox produces a faster way to be asked questions. Agency needs standing goals, its own schedule and the judgement to stay quiet.
The variable most worth regulating in an autonomous agent is its own behaviour. What to measure, what to do when it drifts, and why the agent should act first.
A personal agent sees more of your life than any software you own. That is a strange thing to run as a black box, and open source is the only honest answer.