memory-management

Organize memory graphs with YAML frontmatter and wiki-links for AI agent collaboration.

Updated Apr 26, 2026

Search Tags:#memory #journaling #knowledge-graph #yaml-frontmatter #wiki-links #agent-memory #long-term-memory

Ready to run

npx skills add https://github.com/aliyehiawi/silt-example --skill memory-management-aliyehiawi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-management
Source: https://github.com/aliyehiawi/silt-example/tree/main/memory-management
Command: npx skills add https://github.com/aliyehiawi/silt-example --skill memory-management-aliyehiawi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a structured approach to building a persistent, decodable memory graph for an AI agent, enabling long-term collaboration across work and life.

Core Features & Use Cases

Two-tier memory architecture using YAML frontmatter and Obsidian-style wiki-links for reliable decoding and cross-linking.
Unified memory map across work and life domains, with CLAUDE.md as a hot cache and memory/ for long-term storage.
Supports a deterministic preview-before-write workflow to guard changes as described by the Memory README.

Quick Start

Initialize memory management by bootstrapping CLAUDE.md and the memory tree; then begin adding memory entities to memory/ as you journal and cross-link.

Frequently Asked Questions about memory-management

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

FAQPage Schema

How do I build long-term memory for an AI agent across work and personal domains?▼

You can build long-term AI agent memory by organizing a two-tier architecture using CLAUDE.md as a hot cache and a memory/ directory for persistent storage. This enables reliable cross-domain knowledge retention and collaborative context retrieval.

How do I structure AI agent memory using YAML frontmatter and wiki-links?▼

Structure AI agent memory by applying YAML frontmatter to encode metadata and Obsidian-style wiki-links to connect nodes. This two-tier approach creates a decodable memory graph that supports reliable lookup and cross-referencing.

Can I use Obsidian-style wiki-links to build a knowledge graph for agent memory?▼

Yes, Obsidian-style wiki-links are supported to cross-link memory entities within the memory/ store. Combined with YAML frontmatter, they form a decodable memory graph that enables reliable long-term AI collaboration and context retrieval.

What is the best way to safely update an AI agent's memory store without data loss?▼

The safest way to update an AI memory store is using a deterministic preview-before-write workflow. This approach enforces an immutable journal log and frontmatter-driven metadata, ensuring all memory growth is auditable and reversible.

Does memory management require a specific environment setup to store agent memory?▼

Memory management requires bootstrapping a CLAUDE.md file and a memory/ directory tree. You initialize this environment to begin adding memory entities, journaling, and cross-linking data for long-term AI collaboration.

Why use a preview-before-write workflow for AI agent memory journaling?▼

A preview-before-write workflow guards memory changes by enforcing an immutable journal log and strict metadata validation. This ensures safe, auditable memory growth and prevents unauthorized modifications to the long-term memory graph.