Some Thoughts on Working with Memory Systems
Lessons from adding logging to an agent memory setup — what the data revealed about near-duplicate memories, mid-session query gaps, and what needs fixing next.
I am building a claw-type system that is tightly-coupled to my project management tool (nothing to sell or promote here), and am playing with approaches to memory. At the moment, I am just dumping the chat logs into a simple heartbeat process where the agent extracts useful info from the logs, and that dumps into a Cognee instance.
I realised I had no idea what the interplay was between the agent and Cognee - what was requested, when it was requested, and what was returned. So I added logging for the requests and responses.
It turns out:
- There was a shit-ton of near-duplicate memories stored, because the heartbeat did not check what was already in Cognee. So for certain regular activities, it kept pushing the same thing to Cognee every time.
- The actual agent was only querying Cognee on the first prompt in a new session. So if we changed topic mid-session, nothing was updated.
- I need to add a consolidation activity that every so often goes into Cognee, extracts similar content, and cleans it up.
It all comes back the IT adage: "Trust, but verify"