Persona — Learnable LLM Memory Layer
Writeup in progress. Full research notes covering the salience-vs-frequency problem, contrastive training signal design, Qdrant integration, and benchmark methodology coming soon.
All projectsProject
Persona — Learnable LLM Memory Layer
Research-stage learnable scoring layer that separates access frequency from semantic salience in LLM memory systems — the failure mode that causes drift and recall failures in Mem0, Letta, and Zep on long-horizon tasks.
llmmemoryagentsopen-source
Problem
Existing memory systems (Mem0, Letta, Zep) conflate access frequency with semantic salience, causing memory drift and ranking failures. High-frequency but low-salience memories crowd out critical context, degrading agent performance over long-horizon tasks.
Solution
A learnable scoring layer that separates frequency from salience using contrastive signals from downstream task outcomes. Memories are re-ranked by predicted future utility, not historical access count.
Impact
Research-stage internal prototype demonstrating improved recall@k on memory-dependent benchmarks relative to frequency-based baselines.
Stack
PythonPyTorchQdrantpydanticasyncio