Installation
SGR Agent Core can be installed via pip or Docker. Choose the method that best fits your needs.
Installation via pip
Basic Installation
Install the core package:
Installation with Optional Dependencies
For development, you can install with additional dependencies:
# Install with development dependencies
pip install sgr-agent-core[dev]
# Install with test dependencies
pip install sgr-agent-core[tests]
# Install with documentation dependencies
pip install sgr-agent-core[docs]
Requirements
- Python 3.11 or higher
- OpenAI-compatible LLM API key (or local model endpoint)
Verify Installation
After installation, verify that the package is correctly installed:
You should also be able to use the sgr command-line utility:
Installation via Docker
Using Docker Image
Pull the official Docker image:
Running with Docker
Run the container with your configuration:
docker run -d \
--name sgr-agent \
-p 8010:8010 \
-v $(pwd)/config.yaml:/app/config.yaml:ro \
-v $(pwd)/agents.yaml:/app/agents.yaml:ro \
-v $(pwd)/logs:/app/logs \
-v $(pwd)/reports:/app/reports \
-e SGR__LLM__API_KEY=your-api-key \
ghcr.io/vamplabai/sgr-agent-core:latest \
--config-file /app/config.yaml \
--host 0.0.0.0 \
--port 8010
Using Docker Compose
For a complete setup with frontend, use Docker Compose:
- Copy the example docker-compose file:
- Edit
docker-compose.yamland configure your settings:
services:
backend:
build:
context: .
dockerfile: Dockerfile
command:
- --config-file=/app/config.yaml
- --agents-file=/app/agents.yaml
ports:
- "8010:8010"
volumes:
- ./config.yaml:/app/config.yaml:ro
- ./agents.yaml:/app/agents.yaml:ro
- ./logs:/app/logs
- ./reports:/app/reports
environment:
- SGR__LLM__API_KEY=your-api-key
- SGR__LLM__BASE_URL=https://api.openai.com/v1
- Start the services:
The API server will be available at http://localhost:8010. Interactive API documentation (Swagger UI) is available at http://localhost:8010/docs.
Building from Source
If you want to build the Docker image from source:
git clone https://github.com/vamplabAI/sgr-agent-core.git
cd sgr-agent-core
docker build -t sgr-agent-core:latest .
Configuration
After installation, you'll need to configure your API keys and settings. See the Configuration Guide for detailed instructions.
Quick Configuration
Create a config.yaml file:
llm:
api_key: "your-api-key"
base_url: "https://api.openai.com/v1"
model: "gpt-4o"
execution:
max_iterations: 7
max_clarifications: 3
Or use environment variables:
export SGR__LLM__API_KEY="your-api-key"
export SGR__LLM__BASE_URL="https://api.openai.com/v1"
export SGR__LLM__MODEL="gpt-4o"
Next Steps
- Quick Start Guide — Get started with your first agent
- Configuration Guide — Configure your agents