SuperLocalMemory

v1.0.0Knowledge & Memorystable

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.

agent-memoryagent-reliabilityai-agentsclaude-codecursor
Share:
155
Stars
0
Downloads
0
Weekly
0/5

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

Persistent AI memory MCP server with 4-channel retrieval (semantic, BM25, entity
qualixar

Maintainer

LicenseAGPL 3.0
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx qualixar-superlocalmemory

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 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)
1

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 superlocalmemory
2

Run 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 setup
3

Verify the installation

Run the pre-flight check to confirm all components — embedding model, retrieval pipeline, and MCP server — are correctly installed.

slm doctor
4

Pre-download the embedding model

Download the ~500MB sentence-transformer embedding model in advance to avoid delays on first memory operation.

slm warmup
5

Start 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 mcp
6

Connect 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.

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.

Quick Config Preview

{ "mcpServers": { "qualixar-superlocalmemory": { "command": "npx", "args": ["-y", "qualixar-superlocalmemory"] } } }

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

Read the full setup guide →

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.

33,000+ ServersFree & Open SourceStep-by-Step Guides