Short Term Memory & Long Term Memory
Options
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
07-16-2026 06:37 AM
I am building an Agentic Application on Databricks using LangGraph (Classic Compute — Serverless cant be used so Agent Brickscant be used ).
I want my agent to have two types of memory:
- Short-term memory → Remember the current conversation and tool outputs so the next tool/step has full context.
- Long-term memory → Remember user preferences and behavior across sessions, so the next time the user logs in, the agent already knows them.
What I Need Help With
- Recommended Delta table design for long-term memory (preferences, facts, summaries)? - how to design it
- How to move data from short-term → long-term (when and what to save)?
- How to load long-term memory back into the agent when the user logs in again?
- Any reference examples or notebooks from Databricks for this pattern?
