Separating RAG from memory can make AI agents handle context better
and memory are related in , but they solve different problems. RAG is mainly about finding which context looks useful for the current answer. Memory also needs to track whether something was true at the time, whether it later became outdated, whether it should fade away because it was never important, and whether it should be kept because it explains a decision.
This matters more when the data is not a fixed set of documents, but changing work context from people, , messages, calendars, tasks, and decisions. OpenLoomi is a being used to test this separation.
Key points
- RAG focuses on finding context that seems relevant right now.
- Memory also needs to handle time, staleness, importance, and decision history.
- Changing workplace data makes this harder than searching fixed documents.
- A better may reduce token use by keeping unnecessary context out of prompts.
- OpenLoomi is a testing this idea.