mem0 Memory System
# mem0 MCP Server Installation Guide
✨ **Dream it, Pixel it** ✨
## Quick Install
For a quick automated installation, run:
```bash
./install.sh
```
This script will:
1. Create a Python virtual environment
2. Install all required dependencies
3. Create an activation script for easy environment management
## Installation Options
The installer provides three installation methods:
1. **pip** (default) - Standard Python package installer
2. **uv** - Faster Python package installer
3. **conda** - Anaconda package manager (uses environment.yml)
Choose the option that best fits your workflow.
## Manual Installation
If you prefer to install manually, follow these steps:
### Using pip
```bash
# Create a virtual environment
python3 -m venv .venv
# Activate the environment
source .venv/bin/activate
# Install dependencies
pip install -r requirements.txt
```
### Using uv
```bash
# Install uv if you don't have it
pip install uv
# Create a virtual environment
uv venv .venv
# Activate the environment
source .venv/bin/activate
# Install dependencies
uv pip install -r requirements.txt
```
### Using conda
```bash
# Create a conda environment from environment.yml
conda env create -f environment.yml
# Activate the environment
conda activate mem0-mcp
```
## Environment Variables
Copy the example environment file and update it with your API keys:
```bash
cp .env.example .env
```
Edit the `.env` file with your preferred text editor and add your API keys and configuration:
```shell
# Provider API Keys
OPENAI_API_KEY=your_openai_api_key
ANTHROPIC_API_KEY=your_anthropic_api_key
GOOGLE_API_KEY=your_google_api_key
# Application Settings
APP_NAME=Memory App
# Ollama Settings (for local models)
OLLAMA_BASE_URL=http://localhost:11434
OLLAMA_MODEL=phi4 # or any other model you have installed
# Server Settings
MEM0_DATA_DIR=./memory_data
MEM0_PROVIDER=ollama
MEM0_EMBEDDING_PROVIDER=ollama
```
## Starting the Server
After installation, activate your environment and start the server:
```bash
# Activate the environment
source ./activate_mem0.sh
# Start the server
python server.py
```
## Running the Example
To run the auto memory example:
```bash
# Activate the environment
source ./activate_mem0.sh
# Run the example
python auto_memory_example.py
```
## Troubleshooting
### Missing Module Error
If you encounter a "No module named 'mem0'" or "No module named 'mem0ai'" error:
1. Make sure you've activated the virtual environment
2. Try reinstalling the dependencies:
```bash
pip install -r requirements.txt --force-reinstall
```
### Conda Environment Issues
If you're using conda and encounter issues:
1. Make sure the environment was created correctly:
```bash
conda env list
```
2. If the environment exists but has issues, try recreating it:
```bash
conda env remove -n mem0-mcp
conda env create -f environment.yml
```
### Ollama Connection Issues
If you're using Ollama and encounter connection issues:
1. Make sure Ollama is running:
```bash
curl http://localhost:11434/api/version
```
2. Check that you have the required models installed:
```bash
curl http://localhost:11434/api/tags
```
3. Install missing models if needed:
```bash
ollama pull nomic-embed-text
ollama pull phi4
```
Made with ❤️ by Pink Pixel