memory-systems

Persist and retrieve agent memory across sessions using vector and graph representations.

Updated Aug 23, 2026

Search Tags:#memory #knowledge-graph #vector-store #temporal-knowledge-graph #entity-memory

Ready to run

npx skills add https://github.com/zjh08177/agent-harness --skill memory-systems-zjh08177

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-systems
Source: https://github.com/zjh08177/agent-harness/tree/main/skills/memory-systems
Command: npx skills add https://github.com/zjh08177/agent-harness --skill memory-systems-zjh08177

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Enables agents to persist state across sessions, track entities, and reason over accumulated knowledge by combining vector-based memories with graph-based representations.

Core Features & Use Cases

Memory layering: working, short-term, long-term, and temporal knowledge graphs to support robust recall and reasoning.
Entity memory: track entities across conversations and sessions to preserve identity and relationships.
Knowledge graph integration: structure facts and relationships with temporal validity for time-aware queries.
Memory consolidation: periodic cleanup and pruning to prevent uncontrolled growth while maintaining useful history.
Integration patterns: file-system memory, vector RAG with metadata, and knowledge graphs for scalable memory.

Quick Start

Configure an integrated memory system that persists across sessions, enabling retrieval by entity and time.

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 can configure an integrated memory system using file-system storage, vector RAG with metadata, and knowledge graphs to maintain state and retrieve accumulated knowledge.

What is a temporal knowledge graph for agent memory?▼

A temporal knowledge graph structures facts and relationships with temporal validity, enabling time-aware queries and reasoning over historical data to support robust recall for agents.

How do I track entities across conversations in an AI agent?▼

You track entities across conversations by implementing entity memory layers that preserve identity and relationships, ensuring the agent maintains context without losing prior interaction details.

Can I use numpy to build a vector store for agent memory?▼

Yes, you can use numpy alongside file-system memory and vector RAG with metadata to build scalable memory integration patterns that persist and retrieve agent knowledge efficiently.

How do I prevent uncontrolled growth of agent memory?▼

You prevent uncontrolled memory growth through memory consolidation, which performs periodic cleanup and pruning to remove redundant data while maintaining useful historical context.

What are the memory layers needed for reasoning over accumulated knowledge?▼

Reasoning over accumulated knowledge requires multiple memory layers: working memory, short-term memory, long-term memory, and temporal knowledge graphs to support robust recall.