memory-systems

Persist agent memory across sessions using multi-layer architecture and temporal knowledge graphs.

17.7k|1.5k|Updated Dec 21, 2025

Search Tags:#context #memory #persistence #knowledge-graph #agent-memory #vector-store

Ready to run

npx skills add https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering --skill memory-systems-muratcankoylan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-systems
Source: https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/memory-systems
Command: npx skills add https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering --skill memory-systems-muratcankoylan

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Memory systems provide a persistent, multi-layered memory for agents to maintain continuity across sessions, track entities, and reason over historical data.

Core Features & Use Cases

Multi-layer memory architecture (working, short-term, long-term, entity memory, temporal knowledge graphs) to balance latency and persistence.
Memory consolidation and retrieval patterns to manage growing knowledge bases and prevent drift.
Integration with context systems to load relevant memories just-in-time and support cross-session reasoning for agents across tools and interactions.

Quick Start

Start by modeling the four-memory layers (working, short-term, long-term, and entity memory) and wire them into the agent's context loader to preserve knowledge 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 persist agent memory across sessions?▼

To persist agent memory across sessions, you model a multi-layer memory architecture—working, short-term, long-term, and entity memory—and wire it into the agent's context loader to preserve knowledge continuity.

What is a temporal knowledge graph for agent memory?▼

A temporal knowledge graph for agent memory is a structure that tracks entity validity periods and relationships over time, enabling temporal reasoning and cross-session continuity for historical data.

How do I prevent knowledge drift in a growing agent memory vector store?▼

You prevent knowledge drift in a vector store by applying memory consolidation and retrieval patterns, managing the growing knowledge base by loading relevant memories just-in-time to balance latency and persistence.

Does this multi-layer agent memory approach work with numpy?▼

Yes, the multi-layer agent memory approach works with numpy, which is the required dependency for implementing the vector storage with metadata and memory consolidation logic.

What's the best way to track entities across multiple agent tool interactions?▼

The best way to track entities across multiple tool interactions is using an entity memory layer combined with a temporal knowledge graph, preserving continuity and tracking relationships across sessions and tools.