skills.rest
LGJ-Jonathan
LGJ-JonathanOFFICIAL
Explore all skills by this author →
GitHub

memory-systems

Designs agent memory architectures using vector stores, knowledge graphs, and temporal persistence frameworks.

Updated Mar 26, 2026
Search Tags:#knowledge graph#context engineering#retrieval#agent memory#vector store#mem0#temporal reasoning
One-click install
npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill memory-systems-lgj-jonathan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-systems
Source: https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills/tree/main/context-engineering/skills/memory-systems
Command: npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill memory-systems-lgj-jonathan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve? Agents lose all state when sessions end, forcing users to repeat context and preventing long-term knowledge accumulation. This Skill guides the design of layered memory architectures that persist facts, entities, and relationships across sessions with reliable retrieval. ## Core Features & Use Cases - Framework Comparison: Compares production memory frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee) with benchmark data from LoCoMo, LongMemEval, DMR, and HotPotQA to support selection decisions. - Layered Architecture Guidance: Provides decision tables for working, short-term, long-term, entity, and temporal knowledge graph memory layers, plus retrieval strategies (semantic, entity-based, temporal, hybrid). - Runnable Implementation: Ships a Python module with VectorStore, PropertyGraph, TemporalKnowledgeGraph, and an IntegratedMemorySystem for prototyping before committing to a framework. - Use Case: An engineer building a support agent that must remember user preferences and past issues across conversations uses this Skill to choose Zep for temporal queries, then prototypes entity tracking with the included scripts. ## Quick Start Ask the agent to help you choose and implement a memory framework for an agent that must persist user preferences and entity relationships across sessions.

Frequently Asked Questions about memory-systems

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add long-term memory to an AI agent?▼

Start with the simplest viable layer: file-system memory storing facts as structured JSON with timestamps. Escalate to a vector store like Mem0 when you need semantic search, and add a temporal knowledge graph like Zep/Graphiti only when you need relationship traversal or time-travel queries.

Mem0 vs Zep vs Cognee: which agent memory framework should I choose?▼

Choose Mem0 for fast time-to-production with managed infrastructure, Zep/Graphiti for bi-temporal modeling and temporal queries, and Cognee for dense multi-layer semantic graphs with customizable ECL pipelines. Letta fits agents needing deep self-introspection over their own memory.

What is a temporal knowledge graph for agent memory?▼

A temporal knowledge graph stores facts with validity intervals (valid_from, valid_until) so agents can answer point-in-time queries like where a user lived on a specific date. It prevents stale facts from poisoning context by tracking when facts change.

Does a simple file system work for agent memory?▼

Yes, benchmark evidence shows Letta's filesystem-based agents scored 74% on LoCoMo using basic file operations, beating Mem0's specialized tools at 68.5%. Reliable retrieval matters more than tool sophistication for many use cases.

Why does agent memory retrieval degrade over time?▼

Unbounded memory growth degrades retrieval quality as stale and duplicate facts accumulate. Run periodic consolidation triggered by memory count thresholds or degraded retrieval quality, invalidating outdated facts without discarding history needed for temporal queries.

How do I evaluate an agent memory system?▼

Benchmark against LoCoMo for long-conversation retention, LongMemEval for long-term memory, and HotPotQA for multi-hop reasoning. Treat results as signals for specific retrieval dimensions rather than absolute rankings, and re-benchmark after architecture changes.

Related Skills

Explore More Software Engineering Skills→
VictoriakaeyVictoriakaey

memory-system

Design memory systems for agents to persist and retrieve information across sessions.

Community
Advanced
TECH-HYTECH-HY

memory-systems

Designs agent memory architectures and compares frameworks like Mem0, Zep, Letta, and Cognee.

Official
Advanced
MudraMartinMudraMartin

csharp-concurrency-patterns

Assess .NET concurrency needs and suggest appropriate patterns and tools.

Community
Advanced
bykoleksii-hardobykoleksii-hardo

memory-systems

Integrate persistent semantic memory with vector stores and knowledge graphs.

Community
Advanced