memory-mgr

Manage persistent cross-session memory with a knowledge graph and full-text search.

1|2|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/jaminitachi/SuperClaw --skill memory-mgr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-mgr
Source: https://github.com/jaminitachi/SuperClaw/tree/main/skills/memory-mgr
Command: npx skills add https://github.com/jaminitachi/SuperClaw --skill memory-mgr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the ephemeral nature of AI sessions by providing a persistent, searchable, and structured memory system, ensuring knowledge is retained and accessible across conversations.

Core Features & Use Cases

  • Permanent Storage: Stores information indefinitely using SQLite.
  • Advanced Search: Leverages FTS5 for powerful full-text searching.
  • Knowledge Graph: Organizes information into entities and relationships for deeper understanding.
  • OMC Sync: Bidirectionally syncs with OMC notepad and project memory for seamless integration.
  • Use Case: When working on a complex project, you can ask the AI to "recall what we decided about the database architecture last week," and it will retrieve the relevant, stored information, maintaining project continuity.

Quick Start

Use the memory-mgr skill to remember that the user prefers dark mode for all applications.

Frequently Asked Questions about memory-mgr

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

FAQPage Schema
How do I retain AI session memory across multiple conversations?

To retain AI session memory across conversations, you need a persistent storage system that organizes information into a knowledge graph. This approach uses SQLite to store typed entities and relations indefinitely, ensuring context remains accessible in future sessions.

How does a knowledge graph improve persistent memory search?

A knowledge graph improves persistent memory search by structuring data into typed entities and relationships, enabling deeper contextual understanding. Combined with FTS5 full-text search, it allows precise retrieval of stored information using confidence scoring and access tracking.

What is the best way to sync project memory with an OMC notepad?

The best way to sync project memory with an OMC notepad is using a bidirectional synchronization mechanism. This ensures that knowledge stored in your local memory system and the OMC project notepad remain consistently updated without manual data transfer.

Can I use SQLite and FTS5 for cross-session AI memory storage?

Yes, you can use SQLite and FTS5 for cross-session AI memory storage. SQLite provides permanent indefinite storage for your data, while FTS5 enables powerful full-text searching to quickly retrieve specific information from past sessions.

When do I need confidence scoring and access tracking in a memory system?

You need confidence scoring and access tracking in a memory system when curating large knowledge graphs. These features help evaluate the reliability of stored entities and monitor which information is frequently retrieved, allowing you to maintain high-quality memory.