Skip to content
Railtracks Logo

Build agents in pure Python

Minimal. Extensible. Designed for developers.

Quickstart Browse examples

Our Driving Principle: Flows Are Just Python

In Railtracks, agent behavior is defined directly in Python. There is no configuration language and no external graph definition. Execution order, branching, and looping are expressed using standard control flow.

Building a sequential flow is just like any the code you have written in your life. 

@session
async def flow(user_input):
    a = await call(Agent1, user_input)
    b = await call(Agent2, a)
    c = await call(Agent3, b)
    return c

More complex behavior is built by extending this same pattern.

What This Enables

The same flow model supports a range of agent architectures without introducing new abstractions.

Validation Loops

Iterative workflows such as generation with structured validation.

Research Agent

Sequential and branching steps for search, synthesis, and summarization. Coming soon.

Orchestrator / Worker

A coordinating agent that delegates work to specialized agents or tools. Coming soon.

Suggested Progression

Most users approach Railtracks in roughly this order:

  1. Run the Quickstart to see a complete flow.
  2. Explore one or two architecture examples.
  3. Use the API reference for details.

Community and Contribution

Railtracks is developed in the open.