agentforge-memory

Select and implement memory paradigms for cross-session AI agent persistence.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/Kingxiao/agentforge --skill agentforge-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentforge-memory
Source: https://github.com/Kingxiao/agentforge/tree/main/agentforge-memory
Command: npx skills add https://github.com/Kingxiao/agentforge --skill agentforge-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AgentForge Phase 4 memory system selection helps design AI agents with memory capabilities that persist across sessions by guiding the selection, deployment, and governance of memory paradigms (File Memory, Block Memory, Hierarchical Semantic Memory) and the supporting patterns for progress files and session persistence.

Core Features & Use Cases

  • Decision framework to choose between File Memory, Block Memory, and Hierarchical Semantic Memory based on deployment context (single-user CLI vs multi-tenant SaaS) and privacy requirements.
  • Guidance on progress file design (JSON vs Markdown) and session persistence options (filesystem, SQLite, PostgreSQL).
  • Namespace isolation, memory provider lifecycles, and compliance considerations (data deletion, access control).
  • Reference patterns and implementation notes via the included references.

Quick Start

Describe your agent’s deployment scenario and ask the system to recommend a memory paradigm and initial persistence strategy.

Frequently Asked Questions about agentforge-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design cross-session memory persistence for AI agents?

To implement cross-session memory, choose between File Memory, Block Memory, or Hierarchical Semantic Memory paradigms, then pair the selection with a persistence backend like filesystem, SQLite, or PostgreSQL to retain agent state.

What is the best way to choose a memory architecture for a multi-tenant AI system?

For a multi-tenant system, choose a memory architecture that provides namespace isolation and aligns with GDPR-like deletion and access controls to ensure strict data governance and privacy across tenants.

How does Hierarchical Semantic Memory differ from File Memory for AI agents?

Hierarchical Semantic Memory structures complex data for advanced retrieval, whereas File Memory uses simpler progress files like JSON or Markdown for basic cross-session persistence in single-user CLI agents.

Can I use PostgreSQL for session persistence in multi-tenant AI agents?

Yes, PostgreSQL can be used for session persistence in multi-tenant AI agents, providing a robust backend that supports namespace isolation and compliance requirements for secure data management.

Do I need namespace isolation for single-user CLI agent memory?

Namespace isolation is primarily required for multi-tenant SaaS deployments to separate user data, while single-user CLI agents can typically use simpler File Memory without strict isolation.