i've been building a persistent context layer that captures screen + audio continuously using screenpipe and syncs to a vector db.
how are you handling the relevance scoring? time-based decay alone doesn't work because some old context is critical (architectural decisions) and some recent context is noise. I've left it up to claude code to reason based on the timestamps, and is helpful for the most part, but far from perfect
how are you handling the relevance scoring? time-based decay alone doesn't work because some old context is critical (architectural decisions) and some recent context is noise. I've left it up to claude code to reason based on the timestamps, and is helpful for the most part, but far from perfect