skills.rest
kyopark2014
kyopark2014COMMUNITY
Explore all skills by this author →
WebsiteGitHub

memory-manager

Stores and retrieves agent memory via Markdown files and semantic search.

4|2|Updated Mar 9, 2026
Search Tags:#logs#knowledge management#search#retrieval#memory#persistence
One-click install
npx skills add https://github.com/kyopark2014/agent-plugins --skill memory-manager-kyopark2014
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-manager
Source: https://github.com/kyopark2014/agent-plugins/tree/main/application/skills/memory-manager
Command: npx skills add https://github.com/kyopark2014/agent-plugins --skill memory-manager-kyopark2014

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a robust system for managing an agent's memory, ensuring that important information is stored, retrieved, and organized effectively, preventing data loss and improving recall.

Core Features & Use Cases

  • Memory Persistence: Stores and retrieves information across agent sessions using Markdown files.
  • Semantic Search: Enables searching through historical context using natural language queries.
  • File Management: Utilities for creating, appending to, listing, and archiving memory files.
  • Use Case: An agent needs to remember a user's preference for a specific tool. The memory-manager skill can store this preference in MEMORY.md and retrieve it later using memory_search when the user makes a similar request.

Quick Start

Use the memory_search tool to find information about past project decisions.

Frequently Asked Questions about memory-manager

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

FAQPage Schema
How do I persist agent memory across sessions using Markdown files?▼

Agent memory persistence is managed by storing and retrieving information in structured Markdown files like MEMORY.md, ensuring historical context is preserved across sessions without data loss.

How does semantic search work for retrieving historical agent context?▼

Semantic search for historical context works by using natural language queries to find and retrieve previously stored information, allowing agents to recall past project decisions and user preferences.

What is the best way to organize daily logs and long-term knowledge for agents?▼

Organizing daily logs and long-term knowledge involves using file management utilities to create, append to, list, and archive memory files, curating historical context for effective agent retrieval.

Can I use this memory management approach without any external dependencies?▼

Yes, this memory management approach operates without external dependencies, relying solely on structured Markdown files and dedicated tools for file operations and semantic search.

Why does my agent lose user preferences between different sessions?▼

Agents lose user preferences between sessions without memory persistence. Storing preferences in Markdown files enables agents to retrieve them later using semantic search during similar requests.

What are the limitations of using Markdown files for agent memory management?▼

Using Markdown files for agent memory management requires manual file operations for archiving and organizing, and semantic search effectiveness depends on the structure and curation of the stored knowledge.

Related Skills

Explore More Software Engineering Skills→
JhonHanderJhonHander

deep-agents-memory

Manage ephemeral and persistent memory with file system middleware and composite backend routing.

Community
Advanced
AbdullahMalik17AbdullahMalik17
9

building-rag-systems

Build production RAG systems with semantic chunking and Qdrant vector search.

Community
Advanced
x-cmdx-cmd
4.6k

claw-memory-management

Structure workspace memory into daily logs and persistent knowledge layers.

Official
Intermediate
FrekiManagarmFrekiManagarm

V3 Memory Unification

Migrate fragmented memory backends into AgentDB with HNSW vector search.

Community
Advanced