Memory

Organize long-term details in a file-based memory store with INDEX.md navigation.

18|2|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/yuanyuekejiJN/AivoClaw --skill memory-yuanyuekejijn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Memory
Source: https://github.com/yuanyuekejiJN/AivoClaw/tree/main/extraSkills/memory-1.0.2
Command: npx skills add https://github.com/yuanyuekejiJN/AivoClaw --skill memory-yuanyuekejijn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of your agent outgrowing basic built-in memory by providing an infinite, structured long-term storage system that keeps details organized instead of fragmented.

Core Features & Use Cases

  • Infinite categorized storage: Adds unlimited memory in a dedicated folder so you can keep depth and scale without overwriting built-in memory.
  • Index-driven navigation: Uses INDEX.md files at the root and inside each category so you can quickly find what you stored.
  • Parallel to built-in memory: Runs as a complementary system (~/memory/) that never replaces or conflicts with the agent’s built-in MEMORY.md.
  • Optional one-way sync: Can copy selected items from built-in memory into organized categories under ~/memory/sync/ when needed.

Quick Start

Ask the user what categories they want, then create ~/memory/ with config.md, INDEX.md, and category folders, and store the first real item immediately in the appropriate category file.

Frequently Asked Questions about Memory

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

FAQPage Schema
How do I organize long-term memory and notes for an AI agent beyond its built-in limits?

To organize long-term memory beyond built-in limits, create a dedicated folder with config.md and INDEX.md files to store categorized entries. This infinite structured storage prevents detail loss by keeping projects, people, and knowledge organized without overwriting built-in memory.

What is the best way to index knowledge and notes for semantic search and navigation?

The best way to index notes for navigation is using root and category-level INDEX.md files. This file-based indexing approach creates navigable entry pages allowing quick retrieval of stored decisions, knowledge, and growing collections.

How do I sync selected items from built-in agent memory into organized categories?

To sync selected items from built-in memory, configure a one-way copy operation into a sync folder under your memory directory. This moves specific items into organized categories, complementing rather than replacing the native memory system.

Can I use a file-based memory store without conflicting with the agent's native memory?

Yes, you can use a file-based memory store without conflicts by running it as a parallel system in a separate directory. It operates as a complementary structure that never replaces or overwrites built-in agent memory files.

What are the limitations of using file-based indexing for long-term knowledge management?

A limitation of file-based indexing for knowledge management is the requirement to manually create and maintain directory structures. You must write entries immediately into category files and actively manage indexes to prevent fragmentation as collections scale.