Hacker News new | ask | show | jobs
by rush86999 112 days ago
Nope - just use memory layer with model routing system.

https://github.com/rush86999/atom/blob/main/docs/EPISODIC_ME...
1 comments
atarus 112 days ago
Memory is usually slow and haven't seen many voice agents atleast leverage it. Are you building in text modality or audio as well?
link