Overview
Afterevolve() generates a solution, deploy() turns it into running software. The deployment pipeline handles adaptation, strategy selection, and execution.
Deployment Flow
- Selector: Analyzes code and chooses deployment strategy
- Adapter: Modifies code for the chosen strategy
- Runner: Executes the adapted code
- Software: Unified interface for running and managing
Quick Start
Deployment Strategies
| Strategy | Description | Best For |
|---|---|---|
AUTO | System chooses best strategy | Default |
LOCAL | Run as local Python process | Development, testing |
DOCKER | Run in Docker container | Isolation, reproducibility |
MODAL | Deploy to Modal.com | Serverless, GPU |
BENTOML | Deploy with BentoML | Production ML |
LANGGRAPH | Deploy as LangGraph agent | Agent workflows |
DeployStrategy Enum
Software Interface
All deployments return aSoftware instance with a unified interface:
Response Format
Allrun() calls return a consistent format: