Multiple ways to install MemoryGraph depending on your needs.

Prerequisites

  • Python 3.10+ - Required for the MCP server
  • pip - Python package installer
  • pipx (recommended) - Isolated Python app installer
# Check Python version
python3 --version  # Should be 3.10+

# Install pipx if you don't have it
pip install --user pipx
pipx ensurepath

Installation Methods

Method 1: pipx (Recommended)

pipx installs Python applications in isolated environments and handles PATH automatically.

# Basic installation (SQLite default)
pipx install memorygraphMCP

# With FalkorDBLite (embedded graph database)
pipx install "memorygraphMCP[falkordblite]"

# With FalkorDB client (requires FalkorDB server)
pipx install "memorygraphMCP[falkordb]"

# With Neo4j support (enterprise)
pipx install "memorygraphMCP[neo4j]"

Method 2: pip

Standard pip install (ensure Python bin directory is in PATH).

# Basic installation
pip install memorygraphMCP

# With extras
pip install "memorygraphMCP[intelligence]"

Method 3: From Source

For development or latest unreleased features.

# Clone the repository
git clone https://github.com/gregorydickson/memory-graph.git
cd memory-graph

# Install in development mode
pip install -e ".[dev,intelligence]"

Verify Installation

# Check if memorygraph is available
which memorygraph
memorygraph --version

# Run health check
memorygraph --health

Backend Options

Extra Backend Use Case
(none) SQLite (default) Simple local storage, zero config
falkordblite FalkorDBLite (embedded) Native graph queries without a server
falkordb FalkorDB (client-server) High-performance production deployments
neo4j Neo4j Enterprise features, large-scale
dev Development deps Contributing to MemoryGraph

Next Steps

After installation, you'll need to:

  1. Configure your AI assistant - Connect MemoryGraph to your AI tool
  2. Add memory directives - Tell your AI when to store and recall memories
  3. Optional: Install the plugin - Get auto-invoked skills and slash commands (Claude Code only)

1. Platform Setup Guides

2. Configure Memory Directives

MemoryGraph won't automatically store memories - you need to tell your AI when and what to remember. After setting up your platform, add memory directives to make your AI use memory effectively.

→ Memory Protocol Guide

Pro tip: Copy our recommended memory directives and add them to your CLAUDE.md, .cursorrules, or equivalent configuration file.

3. Optional: Claude Code Plugin

If you're using Claude Code, install the plugin for enhanced functionality: 

/plugin install memory-graph/memorygraph-plugin

The plugin adds auto-invoked skills (solution capture, error tracking), slash commands (/recall, /solve, /learn), and smart hooks.

→ Plugin Documentation