agent-memory

Store facts, learn from experiences, and track entities in a local SQLite database.

4|1|Updated Mar 14, 2026

Search Tags:#learning #agent #memory #sqlite #persistence #entity tracking

Ready to run

npx skills add https://github.com/GPTtang/skill-atlas --skill agent-memory-gpttang

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-memory
Source: https://github.com/GPTtang/skill-atlas/tree/main/skills/ai-agent/agent-memory
Command: npx skills add https://github.com/GPTtang/skill-atlas --skill agent-memory-gpttang

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides AI agents with a persistent memory system to store and retrieve information across different conversations and sessions, enabling them to learn from past experiences and track entities.

Core Features & Use Cases

Fact Storage: Remembers specific pieces of information tagged for easy retrieval.
Experience Learning: Records actions, contexts, outcomes, and insights to build a knowledge base.
Entity Tracking: Maintains profiles for people, projects, or other entities encountered.
Use Case: An agent can remember a user's preference from a previous session, recall a lesson learned from a past failed task, or keep track of a client's contact details.

Quick Start

Use the agent memory skill to remember the fact that the user prefers summaries in bullet points.

Frequently Asked Questions about agent-memory

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

FAQPage Schema

How do I add persistent memory to an AI agent across sessions?▼

Persistent memory for AI agents is achieved by storing facts, learned experiences, and entity profiles in a local SQLite database. This enables long-term context and adaptive learning across different conversations and sessions.

What is entity tracking and how does it work for AI agents?▼

Entity tracking maintains persistent profiles for people, projects, or other entities encountered by the agent. It works by storing entity-specific information in a local SQLite database for easy knowledge recall.

Can I use SQLite for AI agent experience learning and fact storage?▼

Yes, SQLite supports AI agent experience learning and fact storage by recording actions, contexts, outcomes, and insights. Specific pieces of information are tagged in the database for easy retrieval.

How do I make an AI agent remember user preferences from previous sessions?▼

You can make an AI agent remember user preferences by storing them as tagged facts in a persistent memory system. The agent retrieves these specific facts from the local SQLite database in subsequent interactions.

Do I need a specific agent session protocol to use persistent memory?▼

Persistent memory integrates with agent session protocols for proactive memory utilization. The local SQLite database handles storage, while the session protocol enables the agent to actively apply long-term context.