MCPgee
MCPgee
MCPgeeMCPgee

Flywheel Memory

v1.0.0•Knowledge & Memory•stable

MCP Memory Server

ai-toolsbacklinksbenchmarkclaudeclaude-desktop
Share:
45
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Flywheel Memory?

Flywheel Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp memory server

MCP Memory Server

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP Memory Server

Use Cases

Store and retrieve agent memory with knowledge graphs
Access visual dashboard for memory and context management
velvetmonkey

Maintainer

LicenseApache-2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx flywheel-memory

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Flywheel Memory

Flywheel Memory is a local-first MCP memory server that gives AI agents persistent, searchable access to a Markdown vault (such as an Obsidian vault). It combines full-text BM25 search, entity linking, and semantic vector search into a hybrid retrieval system with knowledge-graph traversal — supporting backlinks, forward links, and shortest-path queries between notes. Developers use it so their AI assistant can read, write, and reason across a personal knowledge base rather than starting fresh each session.

Prerequisites

  • Node.js 18 or higher with npm
  • An existing Markdown vault or Obsidian vault directory
  • Git to clone the repository
  • An MCP-compatible client such as Claude Desktop, Cursor, or Codex
1

Clone and build the repository

Clone the flywheel-memory repository, install dependencies, and build the project.

git clone https://github.com/velvetmonkey/flywheel-memory
cd flywheel-memory
npm ci && npm run build
2

Add the server to your MCP client configuration

Point your MCP client at the compiled index.js in the mcp-server package. Replace the path with the absolute path where you cloned the repository.

{
  "mcpServers": {
    "flywheel": {
      "command": "node",
      "args": ["/path/to/flywheel-memory/packages/mcp-server/dist/index.js"]
    }
  }
}
3

Configure environment variables

Set optional environment variables to support multiple vaults or Windows polling. FLYWHEEL_VAULTS accepts a comma-separated list of name:/path pairs for multi-vault setups.

{
  "mcpServers": {
    "flywheel": {
      "command": "node",
      "args": ["/path/to/flywheel-memory/packages/mcp-server/dist/index.js"],
      "env": {
        "FLYWHEEL_VAULTS": "personal:/Users/me/notes,work:/Users/me/work-notes",
        "FLYWHEEL_WATCH_POLL": "false"
      }
    }
  }
}
4

Restart your MCP client

Restart Claude Desktop, Cursor, or whichever client you configured so the server is loaded and begins indexing your vault.

5

Start querying your vault

The server exposes semantic search, entity-linked reads, section-level reads, knowledge-graph traversal (backlinks, forward links, shortest paths), and write tools. Ask the AI to search, read, or update notes naturally.

Flywheel Memory Examples

Client configuration

Claude Desktop configuration for Flywheel Memory with a single vault.

{
  "mcpServers": {
    "flywheel": {
      "command": "node",
      "args": ["/Users/me/flywheel-memory/packages/mcp-server/dist/index.js"],
      "env": {
        "FLYWHEEL_WATCH_POLL": "false"
      }
    }
  }
}

Prompts to try

Example prompts to search and navigate your knowledge vault via Flywheel Memory.

- "Search my vault for notes related to distributed systems"
- "What notes link back to my 'Project Atlas' note?"
- "Read the Architecture section of the microservices note"
- "Find the shortest path between the 'Kafka' note and the 'Event Sourcing' note"
- "Update the TODO section in my weekly review note with today's priorities"
- "What are all the notes that link forward from my 'Reading List' note?"

Troubleshooting Flywheel Memory

File watching doesn't detect changes on Windows

Set the FLYWHEEL_WATCH_POLL environment variable to "true" in your config. Windows filesystem events are unreliable; polling mode ensures the index stays current.

Multiple vaults are not recognized

Set FLYWHEEL_VAULTS in the format `name1:/absolute/path1,name2:/absolute/path2`. Each vault must have a unique name and an absolute path — relative paths are not supported.

Build fails with npm ci errors

Ensure you are using the exact Node.js version compatible with the lockfile. Try deleting node_modules and package-lock.json, then running `npm install && npm run build` to regenerate the lockfile.

Frequently Asked Questions about Flywheel Memory

What is Flywheel Memory?

Flywheel Memory is a Model Context Protocol (MCP) server that mcp memory server It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Flywheel Memory?

Follow the installation instructions on the Flywheel Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Flywheel Memory?

Flywheel Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Flywheel Memory free to use?

Yes, Flywheel Memory is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Flywheel Memory Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Flywheel Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A 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

★ 15.4k

An 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

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (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

★ 5.4k

Build, 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.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "flywheel-memory": { "command": "npx", "args": ["-y", "flywheel-memory"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Flywheel Memory?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides