Skip to main content

​
Prerequisites

Ensure your environment meets the following requirements:
  • Python: 3.10 or higher
  • Package Manager: uv (Recommended) or pip
  • Containerization: Docker 20.10+ and Docker Compose 2.0+
  • Hardware: Minimum 4GB RAM

​
Installation

1

Clone the Repository

git clone https://github.com/EverMind-AI/EverMemOS.git
cd EverMemOS
2

Start Infrastructure Services

EverMemOS requires several backend services to handle storage and retrieval. Use Docker Compose to start them in the background.
docker-compose up -d

​
Included Services

ServiceHost PortPurpose
MongoDB27017Stores primary MemCells and user profiles
Elasticsearch19200Powering keyword search (BM25)
Milvus19530Vector database for semantic retrieval
Redis6379High-speed cache service
Default MongoDB credentials for local development are admin / memsys123.

​
Management Commands

  • Check Status: docker-compose ps
  • View Logs: docker-compose logs -f
  • Stop Services: docker-compose down
Ensure all services are “Running” before proceeding to the next step.
3

Install Dependencies

We recommend using uv for faster dependency resolution.
uv sync
Alternatively, use pip:
pip install -r requirements.txt
4

Configuration

Copy the template environment file and configure your API keys.
cp .env.template .env
Edit .env to add your keys:
LLM_API_KEY=your_llm_key
VECTORIZE_API_KEY=your_embedding_key
Never commit your .env file to version control.

​
Next Steps

Now that you have the system running, try running the demos to see it in action.