MARM Systems
Stop re-explaining yourself to your AI. MARM gives every session persistent memory, cross-agent context sharing, and structured reasoning that builds as you work, not resets. Includes a live web dashboard for browsing memories, logs, and sessions wit
What is MARM Systems?
MARM Systems is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to stop re-explaining yourself to your ai. marm gives every session persistent memory, cross-agent context sharing, and structured reasoning that builds as you work, not resets. includes a live web dashb...
Stop re-explaining yourself to your AI. MARM gives every session persistent memory, cross-agent context sharing, and structured reasoning that builds as you work, not resets. Includes a live web dashboard for browsing memories, logs, and sessions wit
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Stop re-explaining yourself to your AI. MARM gives every ses
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx marm-systemsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MARM Systems
MARM Systems is a persistent memory MCP server designed to give AI agents durable, cross-session recall so that context built in one conversation is available in future sessions without re-explanation. Using semantic embeddings and a named session model, it allows agents to store structured logs, search past memories with hybrid keyword and vector retrieval, and share a common knowledge base across multiple agents running in parallel. It is especially valuable for developers running long-lived projects with Claude Code or other MCP-compatible tools.
Prerequisites
- Python 3.10+ and pip installed, or Docker for containerized deployment
- An MCP-compatible client such as Claude Desktop or Claude Code
- A generated MARM API key for HTTP/Docker deployments
- Optional: Ollama for local embedding model support
Install the MARM server package
Install from PyPI for local stdio usage. The pip package provides the marm-mcp-stdio command used in stdio transport mode.
pip install marm-mcp-serverGenerate an API key for HTTP mode (optional)
If you prefer to run MARM as a Docker HTTP server for multi-agent support, generate a secure API key.
docker run --rm lyellr88/marm-mcp-server:latest --generate-keyRun MARM as a Docker HTTP server
Start the container with the generated key, binding the data directory and exposing port 8001.
docker run -d --name marm-mcp-server \
-p 127.0.0.1:8001:8001 \
-e SERVER_HOST=0.0.0.0 \
-e MARM_API_KEY=your-generated-key \
-v ~/.marm:/home/marm/.marm \
lyellr88/marm-mcp-server:latestConfigure your MCP client
Add MARM to your claude_desktop_config.json or Claude Code settings. Use the stdio command for local installs or an HTTP URL for Docker.
Start storing memories
Converse naturally — MARM's nine tools (marm_smart_recall, marm_context_log, marm_log_session, etc.) are invoked automatically based on what you ask the agent.
MARM Systems Examples
Client configuration (stdio)
Minimal Claude Desktop config for the pip-installed stdio server.
{
"mcpServers": {
"marm-systems": {
"command": "marm-mcp-stdio",
"args": []
}
}
}Client configuration (Docker HTTP)
Claude Desktop config for the Docker HTTP deployment with Bearer authentication.
{
"mcpServers": {
"marm-systems": {
"url": "http://localhost:8001/mcp",
"headers": {
"Authorization": "Bearer your-generated-key"
}
}
}
}Prompts to try
Natural language prompts that trigger MARM's memory tools automatically.
- "Log this session as 'Sprint 12' and record that we finalized the API schema"
- "Search your memory for our discussion about the authentication flow"
- "Show me all entries in the current session"
- "Summarize everything stored in my 'Project Beta' session"
- "Remember this SQL migration script in your notebook"Troubleshooting MARM Systems
marm-mcp-stdio command not found after pip install
Ensure the Python scripts directory is in your PATH. Run pip show marm-mcp-server to see the install location, then add that bin directory to PATH. Using a virtual environment and activating it before running solves this on most systems.
Docker container shows 401 Unauthorized in MCP client
Confirm the Authorization header value matches the key generated by --generate-key exactly. Regenerate with: docker run --rm lyellr88/marm-mcp-server:latest --generate-key and update both the container env var and the client config.
Memories disappear after Docker container is removed
Always mount the data volume with -v ~/.marm:/home/marm/.marm. Without this mount the database is stored inside the container and is lost on removal.
Frequently Asked Questions about MARM Systems
What is MARM Systems?
MARM Systems is a Model Context Protocol (MCP) server that stop re-explaining yourself to your ai. marm gives every session persistent memory, cross-agent context sharing, and structured reasoning that builds as you work, not resets. includes a live web dashboard for browsing memories, logs, and sessions wit It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MARM Systems?
Follow the installation instructions on the MARM Systems GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MARM Systems?
MARM Systems works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MARM Systems free to use?
Yes, MARM Systems is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MARM Systems Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to MARM Systems? 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 MARM Systems 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 MARM Systems?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.