Skip to main content

Stepflow Introduction

Stepflow is a workflow orchestrator that enables you to create and execute AI workflows by combining components from different tools and services, both locally and in the cloud.

As an orchestrator, Stepflow manages workflow execution, data flow, and state persistence, while component servers provide the actual business logic. This separation allows for flexible, scalable architectures where components can execute locally during development or be distributed across multiple machines in production.

Stepflow defines a protocol for component servers, allowing a combination of custom and off-the-shelf components to be orchestrated within a single workflow. By routing specific steps to different component servers, you can create workflows that run across multiple machines, containers, or cloud services. Its modular architecture ensures secure, isolated execution of components—whether running locally or deployed to production.

Stepflow further solves for production problems like durability and fault-tolerance by journalling the results of each component execution, allowing workflows to be resumed from the last successful step in the event of a failure without adding complexity to component servers.

Architecture​

Stepflow consists of a workflow orchestrator that manages the execution of workflows and component servers that provide the actual business logic using the Stepflow protocol or Model Context Protocol.

The orchestrator handles:

  • Workflow execution and step coordination
  • Data flow between components
  • State persistence and fault tolerance
  • Resource management and scaling

Component servers provide:

  • Business logic implementation
  • Domain-specific functionality
  • Integration with external services
  • Custom processing capabilities

During development, the Stepflow orchestrator manages the component servers and MCP servers in subprocesses, communicating over stdio.

Next Steps​