OpenMemory

Provides persistent AI agent memory via a local SQLite database with semantic search capabilities.

1|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/Svtoo/atk-registry --skill openmemory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: OpenMemory
Source: https://github.com/Svtoo/atk-registry/tree/main/plugins/openmemory
Command: npx skills add https://github.com/Svtoo/atk-registry --skill openmemory

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a persistent memory layer for AI agents, enabling them to retain information across conversations, learn user preferences, and avoid repeating past mistakes.

Core Features & Use Cases

  • Long-term Memory Storage: Persists memories in a local SQLite database with semantic search capabilities.
  • User Preference Learning: Captures and recalls user preferences for coding style, tool choices, and task execution.
  • Contextual Awareness: Allows AI to query memory before taking actions, ensuring decisions are informed by past interactions and knowledge.
  • Use Case: An AI agent working on a software project can use OpenMemory to recall the user's preferred testing framework, coding conventions, and previously encountered bugs, leading to more efficient and tailored assistance.

Quick Start

Use OpenMemory to store the fact that the user prefers pytest for all testing tasks.

Frequently Asked Questions about OpenMemory

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

FAQPage Schema
How do I add persistent memory to an AI agent so it remembers user preferences across conversations?

You can add persistent memory to an AI agent by integrating a memory layer that stores and retrieves user preferences in a local SQLite database, allowing the agent to recall past interactions and context across conversations.

What is semantic search for AI memory and how does it help with project context?

Semantic search for AI memory enables agents to query a persistent storage layer for relevant project context and past events, ensuring decisions are informed by previously encountered bugs and coding conventions.

Can I use MCP to integrate a long-term memory database with my AI agent?

Yes, you can use MCP to integrate a long-term memory database with your AI agent, enabling seamless interaction and data persistence across episodic, semantic, and procedural memory sectors.

How do I store and recall user coding conventions and tool choices in an AI agent?

You store and recall user coding conventions by capturing user preferences within the AI's memory layer, which persists data like preferred testing frameworks and tool choices for future retrieval.

Does persistent AI memory support configurable decay rates for different memory types?

Yes, persistent AI memory supports configurable decay rates, allowing you to manage how long episodic, semantic, procedural, emotional, and reflective memories are retained in the database.

What are the limitations of using a local SQLite database for AI agent memory persistence?

Using a local SQLite database for AI agent memory persistence limits data access to the local environment, meaning the stored memories and semantic search capabilities are not available across distributed systems without additional setup.