Memory Systems

If you're building agents that need to remember things across sessions, this walks you through the production memory stack: Mem0 for multi-tenant speed, Zep/Graphiti for temporal knowledge graphs, Letta for self-editing memory, Cognee for semantic graphs with customizable pipelines. It includes benchmark comparisons (DMR, LoCoMo, HotPotQA) so you can set realistic expectations, and it's opinionated about starting simple. The core advice is sound: use the filesystem until retrieval breaks, then add vector search, then add graph structure only when you need multi-hop reasoning. The framework comparison table alone saves hours of documentation skimming. Stays in its lane by routing token optimization and compression work to other skills.

Install to Claude Code

npx -y skills add muratcankoylan/agent-skills-for-context-engineering --skill memory-systems --agent claude-code