MCPgee
MCPgee
MCPgeeMCPgee

SimpleMem

v1.0.0•Knowledge & Memory•stable

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

agentaudiocompressionknowledge-graphlifelong-memory
Share:
3,330
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is SimpleMem?

SimpleMem is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to simplemem: efficient lifelong memory for llm agents — text & multimodal

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

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

Features

  • SimpleMem: Efficient Lifelong Memory for LLM Agents — Text &

Use Cases

Efficient lifelong memory for LLM agents
Text and multimodal memory management
aiming-lab

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx simplemem

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 SimpleMem

SimpleMem is an efficient lifelong memory system for LLM agents that compresses conversations and multimodal inputs (text, images, audio, video) into a semantic knowledge store with multi-view indexing for fast retrieval. It ships three tiers: SimpleMem for text dialogue compression, Omni-SimpleMem for multimodal ingestion, and EvolveMem for self-adapting retrieval that diagnoses failures and tunes its own configuration. An MCP endpoint lets any MCP-compatible AI client read and write memories without running Python directly.

Prerequisites

  • Python 3.10+ for local installation
  • Docker and Docker Compose for the containerized MCP deployment (recommended)
  • An OpenAI-compatible API key (OpenAI, Azure OpenAI, Qwen, or similar) for the embedding and compression LLM
  • A SimpleMem cloud token if using the hosted MCP endpoint at mcp.simplemem.cloud
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Clone the repository and install dependencies

Clone SimpleMem and install the Python package including the optional MCP/HTTP server extras.

git clone https://github.com/aiming-lab/SimpleMem.git
cd SimpleMem
pip install -e .
pip install -e ".[server]"
2

Configure the LLM provider

Edit config.py to set your API key, optional custom base URL (for Qwen or Azure), and the LLM and embedding model names.

# config.py
OPENAI_API_KEY = "your-openai-or-compatible-api-key"
OPENAI_BASE_URL = None  # Set for Qwen/Azure: e.g. "https://your-endpoint/v1"
LLM_MODEL = "gpt-4o-mini"
EMBEDDING_MODEL = "Qwen/Qwen3-Embedding-0.6B"
3

Start the MCP server with Docker Compose

The recommended deployment uses Docker Compose which starts the web UI, REST API, and MCP SSE endpoint together. Set your JWT and encryption secrets in a .env file before starting.

# Create .env with:
# JWT_SECRET_KEY=your_jwt_secret
# ENCRYPTION_KEY=your_encryption_key
# LLM_PROVIDER=openai
docker compose up -d
4

Connect via the hosted cloud endpoint (alternative)

If you prefer not to self-host, use the SimpleMem cloud MCP endpoint. Obtain a token from mcp.simplemem.cloud and add it to your client config.

{
  "mcpServers": {
    "simplemem": {
      "url": "https://mcp.simplemem.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_SIMPLEMEM_TOKEN"
      }
    }
  }
}
5

Configure Claude Desktop for self-hosted deployment

Point Claude Desktop at your local Docker deployment's MCP SSE endpoint. Replace YOUR_TOKEN with the token generated by your Docker instance.

{
  "mcpServers": {
    "simplemem": {
      "url": "http://localhost:8000/mcp/sse?token=YOUR_TOKEN"
    }
  }
}

SimpleMem Examples

Client configuration

Claude Desktop config using the SimpleMem cloud MCP endpoint.

{
  "mcpServers": {
    "simplemem": {
      "url": "https://mcp.simplemem.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_SIMPLEMEM_TOKEN"
      }
    }
  }
}

Prompts to try

Use these prompts with your MCP client to store and retrieve memories through SimpleMem.

- "Remember that our sprint review is every Friday at 3pm and the team lead is Alice"
- "What do you know about my project preferences from previous conversations?"
- "Store this image and remember it as our office floor plan"
- "Search my memories for anything related to the authentication service"
- "What have we discussed about the database migration task?"

Troubleshooting SimpleMem

Docker Compose fails to start with missing environment variable errors

Ensure you have created a .env file in the SimpleMem directory containing JWT_SECRET_KEY, ENCRYPTION_KEY, and LLM_PROVIDER before running docker compose up -d. Copy .env.example if one exists in the repository.

Memory queries return empty results despite adding memories

Confirm that finalize() has been called after adding memories in the Python API — this builds the index. For the MCP server, check that the embedding model specified in config.py is accessible and the API key has permission to call it.

The self-hosted MCP SSE endpoint returns 401 Unauthorized

Retrieve a valid token from the web UI at http://localhost:8000/ after starting Docker Compose. Tokens are generated per-user and are different from the JWT_SECRET_KEY used internally.

Frequently Asked Questions about SimpleMem

What is SimpleMem?

SimpleMem is a Model Context Protocol (MCP) server that simplemem: efficient lifelong memory for llm agents — text & multimodal It connects AI assistants to external tools and data sources through a standardized interface.

How do I install SimpleMem?

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

Which AI clients work with SimpleMem?

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

Is SimpleMem free to use?

Yes, SimpleMem is open source and available under the MIT 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

SimpleMem Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to SimpleMem? 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": { "simplemem": { "command": "npx", "args": ["-y", "simplemem"] } } }

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

Read the full setup guide →

Ready to use SimpleMem?

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