How should AI agents manage memory: markdown notes or vector databases?
This raises a question about how AI agents should remember and manage conversational context. The core issue is whether markdown-based note systems, similar to Obsidian, function as short-term '' for a session, or whether they can actually replace systems entirely.
Opinions are mixed on whether a LLM-wiki approach is more useful than longer-term contextual learning. The question also seeks specific algorithms for moving short-term memory stored in markdown directories into held in , as well as methods for pruning and maintaining that over time.
Key points
- Asks whether Obsidian-style markdown memory acts as daily or actually replaces RAG
- Mixed opinions on whether a LLM-wiki approach beats long-term contextual learning
- Looking for specific algorithms to move short-term markdown memory into long-term storage
- Also asks how should be pruned and maintained over time