memory-manager

Manage AI agent memory with semantic, procedural, and episodic patterns.

Updated Feb 16, 2026
One-click install
npx skills add https://github.com/dsactivi-2/Mujo-Team --skill memory-manager-dsactivi-2
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-manager
Source: https://github.com/dsactivi-2/Mujo-Team/tree/main/skills/memory-manager
Command: npx skills add https://github.com/dsactivi-2/Mujo-Team --skill memory-manager-dsactivi-2

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the critical issue of AI memory management, preventing data loss due to compression and ensuring efficient retrieval of vital information.

Core Features & Use Cases

  • Memory Organization: Implements a robust semantic/procedural/episodic memory architecture.
  • Compression Detection: Proactively warns agents about potential memory compression risks.
  • Automated Snapshots: Creates backups before memory is lost.
  • Semantic Search: Enables efficient searching across different memory types.
  • Use Case: An agent needs to recall a specific workflow for launching a new skill. This Skill allows the agent to quickly search its procedural memory for the exact steps, ensuring consistent and accurate execution.

Quick Start

Run ~/.openclaw/skills/memory-manager/detect.sh to check for compression risks.

Frequently Asked Questions about memory-manager

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

FAQPage Schema
How do I prevent AI agent memory loss during context compression?

To prevent AI agent memory loss during context compression, you need a memory manager that detects compression risks and automates snapshots before data is lost. This approach ensures vital information remains recoverable across sessions.

What is the best way to organize local memory for AI agents?

The best way to organize local memory for AI agents is by implementing a semantic, procedural, and episodic memory architecture. This pattern categorizes different knowledge types to improve retrieval efficiency and maintain context.

How do I search across different AI memory types locally?

You can search across different AI memory types locally using categorized semantic search capabilities. This allows an agent to quickly query specific memory categories, such as recalling exact workflow steps from procedural memory.

Does local AI memory storage work without external API dependencies?

Yes, local AI memory storage can operate without external API dependencies by utilizing file-based storage. This approach ensures privacy, enables local operation, and delivers sub-100ms retrieval times for agent queries.

How do I check for AI agent memory compression risks?

You can check for AI agent memory compression risks by running a dedicated detection script. This proactively warns agents about potential memory compression hazards before they cause irreversible context loss.