memory-systems

Compare agent memory frameworks and design persistence architectures for cross-session knowledge retention.

3|Updated Dec 23, 2025

Search Tags:#state management #knowledge graph #persistence #agent memory #vector store #temporal data

Ready to run

npx skills add https://github.com/boazcstrike/opencode --skill memory-systems-boazcstrike

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of enabling AI agents to retain and recall information across multiple interactions, moving beyond stateless conversations to persistent, context-aware behavior.

Core Features & Use Cases

Memory Framework Comparison: Evaluates and guides the implementation of various agent memory systems (e.g., Mem0, Zep/Graphiti, Letta, LangMem, Cognee).
Persistence Architectures: Designs strategies for storing and retrieving knowledge, including vector stores, knowledge graphs, and temporal data.
Use Case: When building a customer support chatbot that needs to remember past interactions and user preferences to provide personalized and consistent service over time.

Quick Start

Use the memory-systems skill to choose a memory framework for an agent that needs to persist state 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 implement agent memory for cross-session state persistence?▼

Agent memory systems enable persistent, context-aware behavior by storing and retrieving knowledge across multiple interactions. This involves designing persistence architectures using vector stores, knowledge graphs, and temporal data to move beyond stateless conversations.

What is the best way to compare memory frameworks like Mem0, Zep, and LangMem?▼

Comparing memory frameworks like Mem0, Zep, and LangMem involves evaluating their approaches to entity tracking, state persistence, and knowledge graph construction. Production frameworks differ in how they handle temporal data and cross-session knowledge retention architectures.

How do I build a knowledge graph for an AI agent to track entities?▼

Building a knowledge graph for agent entity tracking requires designing persistence architectures that capture relationships and temporal data. Frameworks like Zep/Graphiti and Cognee provide structured approaches for extracting and storing entity connections across sessions.

Do I need a vector store to persist state in an agent memory system?▼

A vector store is a common component for agent memory persistence architectures, enabling semantic retrieval of stored knowledge. However, memory systems also utilize knowledge graphs and temporal data structures depending on the specific cross-session retention requirements.

When should I use a dedicated agent memory framework versus custom state management?▼

Dedicated agent memory frameworks like Letta or Mem0 are necessary when requiring advanced features such as automated entity tracking, knowledge graph construction, and temporal data handling. Custom state management may suffice for simpler persistence needs without complex cross-session retrieval.