Verified:GitHub

memory-systems

Name: memory-systems
Availability: InStock
Author: Sulhi

Creates layered memory architectures with semantic, entity-based, and temporal retrieval patterns for cross-session persistence.

Updated Nov 17, 2025

Search Tags:#agent #retrieval #memory #persistence #knowledge-graph #temporal-knowledge-graph #entity-memory

Ready to run

npx skills add https://github.com/sulhicmz/malnu-backend --skill memory-systems-sulhicmz

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-systems
Source: https://github.com/sulhicmz/malnu-backend/tree/main/.opencode/skills/muratcankoylan-agent-skills-for-context-engineering-memory-systems
Command: npx skills add https://github.com/sulhicmz/malnu-backend --skill memory-systems-sulhicmz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Memory systems address the challenge of losing context across sessions by persisting knowledge, tracking entities, and enabling temporal reasoning for agents.

Core Features & Use Cases

Layered memory architecture (working memory, short-term memory, long-term memory, entity memory, temporal knowledge graphs) to balance latency, persistence, and reasoning.
Memory retrieval patterns (semantic, entity-based, temporal) to support context-aware responses and long-term reasoning.
Knowledge graph integration and cross-session consistency for user profiles and task histories.
Use cases include persistent assistant personas, multi-turn task orchestration, and knowledge management across sessions.

Quick Start

Initialize the memory system within your agent, create an example entity (e.g., user:sample) with basic properties, and simulate a second session to demonstrate cross-session persistence.

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 for multi-turn conversations?▼

To persist agent memory across sessions, implement a layered memory architecture that retains working, short-term, and long-term memory. This ensures multi-turn conversations maintain cross-session continuity by tracking accumulated knowledge and entity state.

What is a temporal knowledge graph and when do I need it for agent memory?▼

A temporal knowledge graph is a memory structure that tracks entities and their relationships over time. You need it when agents must perform temporal reasoning over past interactions, ensuring cross-session consistency for user profiles and task histories.

How do I implement entity memory and retrieval patterns for my agent?▼

Implement entity memory by creating structured entity profiles with basic properties, then apply semantic, entity-based, or temporal retrieval patterns. These patterns retrieve accumulated knowledge dynamically, supporting context-aware responses during multi-turn task orchestration.

Can I use this memory system for persistent assistant personas and task histories?▼

Yes, this memory system supports persistent assistant personas and task histories by integrating knowledge graphs for cross-session consistency. It balances latency and persistence through layered memory architectures, enabling long-term reasoning across sessions.

Does this approach work without external dependencies for knowledge management?▼

Yes, the memory architecture operates without external dependencies, providing built-in consolidation processes and integration guidelines. It handles knowledge management tasks by defining working, short-term, long-term, and entity memory layers internally.

Why does my agent lose context and fail at cross-session continuity?▼

Agents lose context without a defined memory architecture to persist state. Implementing layered memory with consolidation processes and knowledge graph integration enables cross-session continuity, preventing the loss of accumulated knowledge between sessions.