memory-systemslisted

# Memory System Design Use this skill to choose and implement the shallowest persistent memory layer that satisfies retrieval, durability, and reasoning requirements. ## When to Activate - Building agents that must persist knowledge across sessions - Choosing between memory frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee) - Needing to maintain entity consistency across conversations - Implementing reasoning over accumulated knowledge - Designing memory architectures that scale in production - Evaluating memory systems against benchmarks (LoCoMo, LongMemEval, DMR) - Building dynamic memory with automatic entity/relationship extraction and self-improving memory (Cognee) Do not activate this skill for adjacent work owned by other skills: - Token budgets, retrieval scoping, or prefix caching inside one trajectory: `context-optimization`. - Stale or conflicting memories as context poisoning: `context-degradation`. ## Core Concepts Classify memory requirements from volatile context to persistent storage. Default to the simplest layer that meets retrieval needs, because benchmark evidence suggests tool complexity matters less than reliable retrieval for some memory workloads (claim-memory-locomo-filesystem-baseline). Add structure (graphs, temporal validity) only when retrieval quality degrades or the agent needs multi-hop reasoning, relationship traversal, or time-travel queries. ## Detailed Topics ### Production Framework Landscape Select a framework based on the