Hello, I'm Eduardo.
I'm a developer based in Rome, building agents and the tooling that surrounds them. Things I'm thinking about at the moment:
- agents that survive their own context window
- memory that outlives a session
- local-first software with no round trip
- tools small enough to rewrite from scratch
- interfaces that get out of the way
If any of that overlaps with what you're working on, I'd like to hear from you.
I also keep a set of interactive explainers for the parts of machine learning I wanted to understand properly.