Knowledge Graph Memory
A persistent memory server that implements a local knowledge graph using the Kuzu embedded database to store entities, relationships, and observations. It enables AI models to maintain structured long-term context through searchable nodes and compreh
What is Knowledge Graph Memory?
Knowledge Graph Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to persistent memory server that implements a local knowledge graph using the kuzu embedded database to store entities, relationships, and observations. it enables ai models to maintain structured long-t...
A persistent memory server that implements a local knowledge graph using the Kuzu embedded database to store entities, relationships, and observations. It enables AI models to maintain structured long-term context through searchable nodes and compreh
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A persistent memory server that implements a local knowledge
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx knowledge-graph-memory-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Knowledge Graph Memory
Knowledge Graph Memory Server gives AI assistants a persistent, structured memory layer backed by a local Kuzu embedded graph database, allowing Claude to remember entities, relationships, and observations across separate chat sessions. It extends the basic entity-relation model with a dedicated lesson system that captures error patterns, their solutions, verification steps, and success rates — so the AI can learn from past mistakes, not just recall facts. Developers and power users deploy it to give Claude durable context about their codebase, team, ongoing projects, and recurring technical problems.
Prerequisites
- Node.js 18 or higher
- npm or npx available on your PATH
- An MCP-compatible client such as Claude Desktop or Claude Code
- Local write access for the Kuzu database file (stored in the project directory by default)
Clone the repository
Clone the memories-with-lessons-mcp-server repository from GitHub.
git clone https://github.com/T1nker-1220/memories-with-lessons-mcp-server.git
cd memories-with-lessons-mcp-serverInstall dependencies
Install the Node.js dependencies including the Kuzu embedded database client.
npm installBuild the server
Compile the TypeScript source to JavaScript.
npm run buildConfigure your MCP client
Add the server to your MCP client's configuration file. The server uses npx to run; adjust the path if running from a local build. No API keys or external services are required — the graph database is stored locally.
{
"mcpServers": {
"knowledge-graph-memory": {
"command": "npx",
"args": ["knowledge-graph-memory-server"]
}
}
}Restart your MCP client
Restart Claude Desktop or your client after saving the configuration. The memory tools (create_entities, create_relations, add_observations, search_nodes, create_lesson, etc.) will appear in the available tools list.
Knowledge Graph Memory Examples
Client configuration (Claude Desktop)
Full claude_desktop_config.json entry for the Knowledge Graph Memory server. For a local build, replace the npx command with the path to your built dist/index.js file.
{
"mcpServers": {
"knowledge-graph-memory": {
"command": "npx",
"args": ["knowledge-graph-memory-server"]
}
}
}Prompts to try
These prompts demonstrate entity creation, observation tracking, relationship building, and lesson capture across the available tools.
- "Remember that John Smith works at Anthropic and prefers morning meetings"
- "Create an entity for my project 'auth-refactor' and note that it depends on the users table"
- "Search the knowledge graph for anything related to authentication errors"
- "Show me everything you remember about my team members"
- "Record a lesson: when npm install fails with ERESOLVE, the fix is to add --legacy-peer-deps"Troubleshooting Knowledge Graph Memory
npx fails with 'package not found' or the server does not start
Try installing the package globally first with 'npm install -g knowledge-graph-memory-server', then use the global binary in your config instead of npx. Alternatively, clone and build locally and point the config at your 'dist/index.js' file.
Entities created in one session are not visible in a new chat
The Kuzu database file must persist on disk between sessions. Check that the server writes to a fixed path (not a temp directory). Confirm the same server process reads from the same data directory on restart.
add_observations fails with 'entity does not exist'
Observations can only be added to entities that already exist in the graph. Use create_entities first to create the entity, then add_observations. Use read_graph or search_nodes to confirm the entity name before adding observations.
Frequently Asked Questions about Knowledge Graph Memory
What is Knowledge Graph Memory?
Knowledge Graph Memory is a Model Context Protocol (MCP) server that persistent memory server that implements a local knowledge graph using the kuzu embedded database to store entities, relationships, and observations. it enables ai models to maintain structured long-term context through searchable nodes and compreh It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Knowledge Graph Memory?
Follow the installation instructions on the Knowledge Graph Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Knowledge Graph Memory?
Knowledge Graph Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Knowledge Graph Memory free to use?
Yes, Knowledge Graph Memory is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Knowledge Graph Memory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Knowledge Graph Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Knowledge Graph Memory in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Knowledge Graph Memory?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.