Memory Systems

muratcankoylan/agent-skills-for-context-engineering

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.

skills.sh installs: 321
GitHub stars: 18.3K
last updated: May 26, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Memory System Design

Memory provides the persistence layer that allows agents to maintain continuity across sessions and reason over accumulated knowledge. Simple agents rely entirely on context for memory, losing all state when sessions end. Sophisticated agents implement layered memory architectures that balance immediate context needs with long-term knowledge retention. The evolution from vector stores to knowledge graphs to temporal knowledge graphs represents increasing investment in structured memory for improved retrieval and reasoning.

When to Activate

Activate this skill when:

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)

SKILL.md on GitHub