MARM-Systems

Overview

MARM (Memory Accurate Response Mode) is a universal MCP server that enables cross-platform AI memory, multi-agent coordination, and context sharing. It provides semantic search, persistent cross-session memory, and smart recall capabilities, allowing AI agents to remember and build on prior work consistently. The server supports multiple transport protocols including HTTP, STDIO, and WebSocket, making it compatible with various AI clients like Claude, Gemini, and Qwen.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• search_memory

  Search through persistent memory using semantic similarity

  Try:Find information about the previous project requirementsTry:What decisions were made about the API design?
• log_session

  Log current conversation session to persistent memory

  Try:Save this conversation for future referenceTry:Document our discussion about the implementation
• create_notebook

  Create a new persistent notebook entry

  Try:Create a new notebook for project documentationTry:Start a tracking log for this issue
• query_memory

  Query structured memory with specific criteria

  Try:Find all code snippets related to authenticationTry:Retrieve all project decisions from last week
• classify_content

  Automatically classify content into memory categories

  Try:Categorize this code snippetTry:Classify this conversation as project-related
• generate_summary

  Generate a semantic summary of logged conversations

  Try:Summarize our last discussionTry:Create a summary of all project decisions
• share_memory

  Share memory across different AI agents

  Try:Share this information with ClaudeTry:Make this decision available to other AI tools
• clear_memory

  Clear specific memories or reset entire memory pool

  Try:Remove old project dataTry:Clear all temporary information
• export_memory

  Export memory data in various formats

  Try:Export my conversation history as JSONTry:Prepare a report of all project decisions
• auto_log

  Enable automatic logging of conversations

  Try:Turn on automatic session loggingTry:Set up auto-logging for this project
• manage_sessions

  Manage persistent sessions across conversations

  Try:Show all active sessionsTry:Resume the previous coding session
• configure_memory

  Configure memory storage and retrieval parameters

  Try:Set up memory for this specific projectTry:Configure memory retention settings

Comparable tools

Installation

docker pull lyellr88/marm-mcp-server:latest
docker run -d --name marm-mcp-server -p 8001:8001 -v ~/.marm:/home/marm/.marm lyellr88/marm-mcp-server:latest
claude mcp add --transport http marm-memory http://localhost:8001/mcp

pip install marm-mcp-server==2.2.6
pip install -r marm-mcp-server/requirements.txt
python marm-mcp-server
claude mcp add --transport http marm-memory http://localhost:8001/mcp

pip install marm-mcp-server==2.2.6
pip install -r marm-mcp-server/requirements_stdio.txt
claude mcp add --transport stdio marm-memory-stdio python "path/to/marm-mcp-server/server_stdio.py"
python marm-mcp-server/server_stdio.py

{
  "mcpServers": {
    "marm-memory": {
      "httpUrl": "http://localhost:8001/mcp",
      "authentication": {
        "type": "oauth",
        "clientId": "local_client_b6f3a01e",
        "clientSecret": "local_secret_ad6703cd2b4243ab"
      }
    }
  }
}

FAQ

What makes MARM different from other memory solutions?

MARM is specifically designed as an MCP server, providing persistent memory at the protocol level. It works across different AI clients and maintains conversation continuity regardless of which tool you're using.

How does MARM handle authentication?

MARM uses OAuth 2.0 for authentication. For development, it includes mock credentials that can be replaced with proper OAuth providers in production environments.

Compare MARM-Systems with