Honestly the fact that we're still modeling agent harnesses like chat and strapping them into shell sessions instead of building async actor systems with sandboxed OS functionality access actors is bananas to me. So much easy wins can be had just by building on right abstractions... Hopefully will get enough time to play with this idea soon on my own.
I'm actually taking the time to hash out the details to do this as a side experiment project, but basically what I read this project as showing is that if you leverage asynchrony you can let agents be more efficient - and you get this "for free" if you model your "agents" as actors that interact with the system through message passing. Then all the system operations become messages to different actors, need to read a file => message the fs actor => get reply from FS actor as a message when it's done. You'd probably need some out of mailbox ways to share blob resources and sockets for realtime (audio), but for the most part simple message passing should handle most of what LLM agents do.
Actors can have identities and roles for RBAC, etc. you - cross agent communication is the same as sending any other message to a actors.
Not to mention that actors can be on your device, another device, etc. whatever the router can resolve - it's transparent to the agents.
I think you nailed it. I have my own agent harness that's designed with inspiration from erlang/elixir. It seems to be a natural fit for indeterministic output and failures.
rafaelmn · · focus · HN ↗
dirtbag__dad · · focus · HN ↗
rafaelmn · · focus · HN ↗
Actors can have identities and roles for RBAC, etc. you - cross agent communication is the same as sending any other message to a actors.
Not to mention that actors can be on your device, another device, etc. whatever the router can resolve - it's transparent to the agents.
ibash · · focus · HN ↗