memory-systems

Design layered memory architectures with vector stores and temporal knowledge graphs.

2|Updated Dec 24, 2025

Search Tags:#agent #retrieval #memory #knowledge-graph #persistent-memory #vector-store #temporal-graph

Ready to run

npx skills add https://github.com/Asmayaseen/hackathon-2 --skill memory-systems-asmayaseen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-systems
Source: https://github.com/Asmayaseen/hackathon-2/tree/main/.claude/skills/memory-systems
Command: npx skills add https://github.com/Asmayaseen/hackathon-2 --skill memory-systems-asmayaseen

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Memory systems provide the persistence layer for agents, enabling state to survive across sessions and ensuring consistency of entities and knowledge over time.

Core Features & Use Cases

Layered memory architectures (working, short-term, long-term, and temporal knowledge graphs) to balance latency, persistence, and reasoning.
Persistent storage and retrieval via vector stores and graph-based memories for scalable retrieval and relational reasoning.
Context integration and memory consolidation to enable just-in-time loading, privacy considerations, and memory growth management.
Use Case: a chatbot that remembers user preferences and past interactions to personalize responses and maintain entity continuity across sessions.

Quick Start

Store a memory for an entity, then retrieve memories to verify results. For example, remember that user123 prefers coffee at a given time and later query memories for user123 to see related facts.

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 state across sessions for a conversational system?▼

You can persist agent state across sessions by implementing a layered memory architecture that uses a vector store and temporal knowledge graph for storage, retrieval, and context integration. This ensures entity continuity as interactions evolve.

What is a temporal knowledge graph and when do I need it for autonomous agents?▼

A temporal knowledge graph is a memory layer that tracks how entities and facts evolve over time. You need it for autonomous agents that must reason over evolving knowledge, maintaining relational context beyond simple static retrieval.

How do I store and retrieve user preferences in a chatbot memory system?▼

To store and retrieve user preferences, you save entity-specific facts to the memory system, such as noting a user prefers coffee. You then query the memory store for that user to retrieve related facts and personalize responses.

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

Yes, numpy is the required dependency for building this persistent memory architecture. It provides the numerical operations needed to support the vector store implementation for scalable memory storage and retrieval.

What's the best way to structure working, short-term, and long-term memory for agents?▼

The best way to structure agent memory is using a layered model that balances latency, persistence, and reasoning. This architecture separates working, short-term, long-term, and temporal graphs to manage just-in-time loading and memory growth.

Why does my chatbot lose entity continuity between different sessions?▼

Your chatbot loses entity continuity because it lacks a persistent memory layer. Implementing memory consolidation and context integration with a vector store ensures state survives across sessions and maintains knowledge consistency.