memory

Store persistent facts and searchable event logs using grep.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/GML-FMGroup/cloud_agent --skill memory-gml-fmgroup
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/GML-FMGroup/cloud_agent/tree/main/cloud_agent/skills/memory
Command: npx skills add https://github.com/GML-FMGroup/cloud_agent --skill memory-gml-fmgroup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a structured way to store and recall important information, ensuring consistency and context in your interactions.

Core Features & Use Cases

  • Long-Term Fact Storage: Persistently store user preferences, project details, and relationship information in MEMORY.md.
  • Event Logging: Maintain an append-only log of past events in HISTORY.md for searchable recall.
  • Use Case: When discussing a project, the Skill can recall specific API authentication details or user preferences previously stored, ensuring continuity and accuracy.

Quick Start

Search for past events related to a specific meeting using grep.

Frequently Asked Questions about memory

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

FAQPage Schema
How do I store persistent context and user preferences for long-term recall?

You can store persistent context and user preferences by writing them to a long-term fact file. This ensures important details like project information and relationships remain available for future interactions, ensuring consistency.

What is the best way to maintain a searchable event log of past interactions?

Maintain a searchable event log by appending past events to a dedicated history file. You can then use grep to efficiently search this log for specific past events or historical interactions.

Can I use grep to search historical event logs for specific meeting details?

Yes, you can use grep to search the append-only event log for specific meeting details. This enables efficient recall of historical interactions and context-aware task execution.

How does a two-layer memory system work for managing project context?

A two-layer memory system separates persistent facts from an append-only event log. This structure facilitates recalling specific details like API authentication while keeping historical interactions searchable.

Do I need any specific dependencies to manage long-term facts and event logs?

No specific dependencies are required to manage long-term facts and event logs. The system relies on basic file storage and standard search utilities like grep for recalling information.