​
Prerequisites

Before you begin, make sure you have the following installed:
Self-hosted requires an enterprise license. Book a call with our sales team to get started.

​
Installation Steps

​
1. Clone the Repository

git clone https://github.com/qaml-ai/camelAI-docker-compose.git
cd camelAI-docker-compose

​
2. AWS ECR Authentication

Since the camelAI image is stored in Amazon ECR, you’ll need to authenticate Docker to access it:
  1. Install the AWS CLI if you haven’t already
  2. Configure your AWS credentials: 
    aws configure
    Enter your:
    • AWS Access Key ID
    • AWS Secret Access Key
    • Default region (us-west-2)
    • Default output format (json)
  3. Authenticate Docker with ECR: 
    aws ecr get-login-password --region us-west-2 | docker login --username AWS --password-stdin 904534089871.dkr.ecr.us-west-2.amazonaws.com
  4. Verify you have the necessary IAM permissions:
    • The AmazonEC2ContainerRegistryReadOnly policy is required
    • Or a custom policy with ecr:GetAuthorizationToken and ecr:BatchCheckLayerAvailability permissions

​
3. Configure Environment Variables

The repository includes a .env.docker template file. Copy it and update the values: 
cp .env.docker .env.docker.local
Edit .env.docker.local with your configuration:
  • Set a secure DJANGO_SECRET_KEY
  • Update POSTGRES_PASSWORD with a secure password
  • Configure at least one LLM provider:
    • OpenAI API key
    • Anthropic API key
    • AWS Bedrock credentials
    • Azure OpenAI credentials
See our Environment Variables guide for details.

​
4. Start the Application

Run the following command to start camelAI in production mode: 
docker compose -f docker-compose.prod.yml up -d
This will start the following services:
  • camel – The main application
  • huey – Background task worker
  • nginx – Reverse proxy
  • pgvector – PostgreSQL with vector extension
  • redis – Queue and caching layer

​
5. Create a Superuser

Once the services are running, create your initial superuser account: 
docker compose exec camel python manage.py createuser
Follow the prompts to set up your superuser credentials.

​
6. Access the Web Interface

Visit the following URL in your browser: 
http://localhost:8000
Log in using the superuser credentials you just created.

​
Troubleshooting

If you encounter any issues during installation:
  1. Check that Docker and Docker Compose are running
  2. Verify your environment variables are correctly set
  3. Ensure you’re authenticated with AWS ECR
  4. Check the logs using: 
    docker compose logs
For more detailed troubleshooting, visit our Troubleshooting Guide.