SuperLocalMemory
Persistent AI memory MCP server with 4-channel retrieval (semantic, BM25, entity graph, temporal). 74.8% on LoCoMo benchmark with zero cloud dependency. Works with Claude, Cursor, VS Code Copilot, and 17+ AI tools. EU AI Act compliant. MIT license.
What is SuperLocalMemory?
SuperLocalMemory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to persistent ai memory mcp server with 4-channel retrieval (semantic, bm25, entity graph, temporal). 74.8% on locomo benchmark with zero cloud dependency. works with claude, cursor, vs code copilot, and...
Persistent AI memory MCP server with 4-channel retrieval (semantic, BM25, entity graph, temporal). 74.8% on LoCoMo benchmark with zero cloud dependency. Works with Claude, Cursor, VS Code Copilot, and 17+ AI tools. EU AI Act compliant. MIT license.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Persistent AI memory MCP server with 4-channel retrieval (se
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx qualixar-superlocalmemoryConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use SuperLocalMemory
SuperLocalMemory (qualixar/superlocalmemory) is a research-backed persistent AI memory MCP server that stores all data locally with zero cloud dependency, achieving 74.8% accuracy on the LoCoMo benchmark using a 5-channel hybrid retrieval system combining semantic search, BM25, entity graph, temporal reasoning, and Hopfield networks. It integrates with 17+ AI tools including Claude, Cursor, VS Code Copilot, Windsurf, and JetBrains, providing continuous cross-session memory without any data leaving your machine. Developers and privacy-conscious users deploy it to give their AI assistants persistent, accurate memory that compounds over time while remaining fully EU AI Act compliant.
Prerequisites
- Node.js 14+ for the recommended npm installation, or Python 3.11+ for pip
- Approximately 700MB of disk space for embedded models and dependencies (no GPU required)
- Optional: Ollama installed for Mode B (local LLM-enhanced answers)
- An MCP-compatible client: Claude Desktop, Claude Code, Cursor, VS Code, or similar
- Internet access only for initial model download (~500MB embedding model on first run)
Install SuperLocalMemory
Install via npm (recommended) to get the 'slm' CLI, or via pip if you prefer Python package management.
npm install -g superlocalmemory
# OR
pip install superlocalmemoryRun the interactive setup
Run 'slm setup' to choose your operating mode. Mode A is zero-cloud (recommended for privacy), Mode B adds a local Ollama LLM, Mode C allows optional cloud LLM for maximum accuracy.
slm setupVerify the installation
Run the pre-flight check to confirm all components — embedding model, retrieval pipeline, and MCP server — are correctly installed.
slm doctorPre-download the embedding model
Download the ~500MB sentence-transformer embedding model in advance to avoid delays on first memory operation.
slm warmupStart the MCP server
Launch the MCP server. For HTTP transport (recommended), run 'slm mcp' as a background daemon and connect all your IDEs to the shared endpoint.
slm mcpConnect your AI clients
Add the SuperLocalMemory MCP server to each AI tool you want to give persistent memory. Use HTTP transport for a single shared daemon across all clients.
SuperLocalMemory Examples
Client configuration
Add one of these configurations to your MCP client. HTTP transport (v3.6.7+) is recommended so all your AI tools share one memory instance.
{
"mcpServers": {
"superlocalmemory": {
"type": "http",
"url": "http://127.0.0.1:8765/mcp/"
}
}
}
// OR stdio (universal compatibility):
{
"mcpServers": {
"superlocalmemory": {
"command": "slm",
"args": ["mcp"]
}
}
}Prompts to try
These prompts demonstrate how your AI assistant can store and retrieve persistent memories across sessions.
- "Remember that this project uses React 18 with TypeScript and Vite, deployed on Vercel"
- "What tech stack does this project use?"
- "Remember that the team standup is every Tuesday and Thursday at 10am PST"
- "What meetings does the team have?"
- "Forget the note about the deprecated v1 API endpoint"Troubleshooting SuperLocalMemory
Memory retrieval is slow on the first few queries
The embedding model (~500MB) downloads on first use if 'slm warmup' was not run. Run 'slm warmup' explicitly to pre-download it. Subsequent queries use the cached model and are fast.
Multiple IDE clients have separate memory stores
Switch to HTTP transport: run 'slm mcp' as a persistent daemon and configure all clients to use 'http://127.0.0.1:8765/mcp/' instead of stdio. This ensures all AI tools share the same memory instance.
Recall accuracy is low for older memories
Run 'slm consolidate --cognitive' to extract reusable patterns from memory clusters and improve retrieval. Also run 'slm decay' to review the memory lifecycle and 'slm quantize' for smart compression of older entries.
Frequently Asked Questions about SuperLocalMemory
What is SuperLocalMemory?
SuperLocalMemory is a Model Context Protocol (MCP) server that persistent ai memory mcp server with 4-channel retrieval (semantic, bm25, entity graph, temporal). 74.8% on locomo benchmark with zero cloud dependency. works with claude, cursor, vs code copilot, and 17+ ai tools. eu ai act compliant. mit license. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install SuperLocalMemory?
Follow the installation instructions on the SuperLocalMemory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with SuperLocalMemory?
SuperLocalMemory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is SuperLocalMemory free to use?
Yes, SuperLocalMemory is open source and available under the AGPL 3.0 license. You can use it freely in both personal and commercial projects.
SuperLocalMemory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to SuperLocalMemory? 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 SuperLocalMemory 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 SuperLocalMemory?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.