MemOS
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
What is MemOS?
MemOS is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 ...
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
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MemOS (Memory Operating System) is a memory management opera
Use Cases
Maintainer
Works with
Installation
NPM
npx -y memos-mcp-serverManual Installation
npx -y memos-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MemOS
MemOS (Memory Operating System) is an MCP server that gives AI systems persistent, searchable long-term memory — letting them remember conversation context, user preferences, and knowledge across sessions the way humans do. It connects to the MemOS API and exposes tools for inserting messages, querying stored memories, managing knowledge bases, and uploading documents so your AI agent can actively recall and apply past context rather than starting fresh each time.
Prerequisites
- Node.js 18+ installed
- A MemOS API key (sign up at the MemOS / MemTensor platform to obtain MEMOS_API_KEY)
- A stable user identifier for MEMOS_USER_ID (non-PII, deterministic per user)
- An MCP-compatible client such as Claude Desktop, Cursor, or Cline
Obtain your MemOS API credentials
Sign up at the MemTensor / MemOS platform to get your API key. You will also need to decide on a stable, non-PII user identifier (e.g. a UUID) that uniquely identifies each end-user in the system.
Install the MemOS MCP server
Use npx to run the server directly — no global install required. The package is published as memos-mcp-server on npm.
npx -y memos-mcp-serverAdd the server to your MCP client configuration
Open your Claude Desktop (or other client) config file and add the MemOS server entry with your credentials as environment variables.
{
"mcpServers": {
"memos": {
"command": "npx",
"args": ["-y", "memos-mcp-server"],
"env": {
"MEMOS_API_KEY": "your-api-key-here",
"MEMOS_USER_ID": "user-uuid-stable",
"MEMOS_CHANNEL": "GITHUB"
}
}
}
}Restart your MCP client
Restart Claude Desktop (or your chosen client) so it picks up the new server configuration. The MemOS tools should appear in the available tool list.
Create a knowledge base and start storing memories
Use the create_knowledge_base tool to set up a named container, then use add_message to begin logging conversation turns. The server will persist and index them for later retrieval.
MemOS Examples
Client configuration
Claude Desktop config block for the MemOS MCP server with all required environment variables.
{
"mcpServers": {
"memos": {
"command": "npx",
"args": ["-y", "memos-mcp-server"],
"env": {
"MEMOS_API_KEY": "your-memos-api-key",
"MEMOS_USER_ID": "550e8400-e29b-41d4-a716-446655440000",
"MEMOS_CHANNEL": "MCPMARKETCOM"
}
}
}
}Prompts to try
Example prompts to exercise MemOS memory management capabilities once the server is connected.
- "Remember that my preferred coding language is TypeScript and I work on a SaaS product."
- "Search my memories for anything related to our last discussion about database schema design."
- "Create a knowledge base called 'project-alpha' and upload this requirements document to it."
- "What do you know about my past preferences and decisions?"
- "Delete all memories tagged with the topic 'deprecated-feature'."
- "Show me my full user profile and memory summary."Troubleshooting MemOS
Server fails to start with 'Unauthorized' or 401 errors
Verify MEMOS_API_KEY is set correctly in the env block. Check that the key has not expired and that MEMOS_USER_ID is a stable, non-empty string — an empty or changing user ID will cause authentication issues.
search_memory returns no results despite previous add_message calls
Memory indexing may have a short delay. Wait a few seconds and retry. Also confirm MEMOS_CHANNEL matches the value used when messages were originally inserted, since memories are partitioned by channel.
npx command not found or hangs on first run
Ensure Node.js 18+ is installed and npx is on your PATH. Run 'node --version' to confirm. On first run, npx needs to download the package — ensure you have internet access and the npm registry is reachable.
Frequently Asked Questions about MemOS
What is MemOS?
MemOS is a Model Context Protocol (MCP) server that 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 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MemOS?
Install via npm with the command: npx -y memos-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with MemOS?
MemOS works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MemOS free to use?
Yes, MemOS is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
MemOS Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to MemOS? 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.
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Cipher
★ 4.8kCipher is an opensource memory layer specifically designed for coding agents. Compatible with Cursor, Windsurf, Claude Desktop, Claude Code, Gemini CLI, AWS's Kiro, VS Code, and Roo Code through MCP, and coding agents, such as Kimi K2.
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 MemOS 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 MemOS?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.