memory-graph

Name: memory-graph
Availability: InStock
Author: macroMan

Create and persist durable facts, entities, and relationships via MCP Memory server.

Updated Aug 23, 2026

Search Tags:#context management #knowledge graph #MCP #relationships #persistent memory #entity recognition

Ready to run

npx skills add https://github.com/MacroMan5/claude-code-workflow-plugins --skill memory-graph

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-graph
Source: https://github.com/MacroMan5/claude-code-workflow-plugins/tree/main/.claude/skills/memory-graph
Command: npx skills add https://github.com/MacroMan5/claude-code-workflow-plugins --skill memory-graph

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @modelcontextprotocol/server-memory, and includes references (resource) components.

What problem does it solve?

AI agents often lose context between sessions, requiring constant re-prompting of durable facts, entities, and relationships. This Skill provides persistent memory.

Core Features & Use Cases

Persistent Knowledge Graph: Creates, updates, searches, and prunes a knowledge graph using the MCP Memory server, storing durable facts and relationships across sessions.
Automated Context Capture: Proactively identifies and suggests storing new durable facts (e.g., requirements, decisions, owners, IDs, endpoints) as they emerge.
Use Case: When you discover a new service owner, a critical API endpoint, or a dependency between components, use this skill to store it in memory for future sessions, ensuring consistent context.

Quick Start

Remember that 'service:api' is owned by 'person:alice' and depends on 'service:database'.

Frequently Asked Questions about memory-graph

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

FAQPage Schema

How do I maintain persistent memory across AI agent sessions?▼

Persistent memory stores durable facts, entities, and relationships in a knowledge graph so agents retain context between sessions without re-prompting. This Skill creates and manages that graph using the MCP Memory server, automatically capturing new discoveries like service owners, API endpoints, and component dependencies.

How do I build a knowledge graph that tracks entities and relationships?▼

A knowledge graph organizes entities (people, services, endpoints) and their relationships (ownership, dependencies) into searchable nodes. This Skill provides tools to create entities, add observations with sources, establish relations, and prune outdated information—ensuring deduplication and atomic, idempotent operations.

Can I automatically capture and store new facts as they emerge during work?▼

Yes. This Skill proactively identifies emerging durable facts—requirements, decisions, owners, IDs, endpoints—and suggests storing them in memory. It records atomic observations with optional sources and routes updates via defined playbooks, so critical context is never lost.

What's the best way to organize and search stored relationships between services and components?▼

The knowledge graph indexes relationships by entity type and attributes, allowing fast search and retrieval. You interact via MCP Memory tools (search_nodes, read_graph, open_nodes) to query connections and navigate the graph without manual reconstruction each session.

When should I prune or remove outdated entities from the knowledge graph?▼

Prune when facts become stale, services sunset, or ownership changes. This Skill supports safe, idempotent delete operations with clear error handling, letting you maintain accuracy and reduce noise in stored memory over time.

Does this work with existing MCP Memory server setups?▼

Yes. The Skill integrates via fully-qualified MCP Memory tool names (mcp__memory__create_entities, add_observations, create_relations, delete_entities, read_graph, search_nodes, open_nodes), requiring only the @modelcontextprotocol/server-memory dependency.