railtracks 1.1.8

The Railtracks Framework for building resilient agentic systems in simple python

Helpful Links

📘 Documentation
🚀 Examples
🛠 API Reference
💬 Join Discord

What is Railtracks?

Railtracks is a lightweight agentic LLM framework for building modular, multi-LLM workflows. Unlike other frameworks like LangGraph and Google ADK, Railtracks focuses on:

• Simple Python-first APIs -> no graphs, just regular Python code
• Built-in visualization and debugging tools -> understand and trace your agent flows visually
• Zero setup overhead -> run it like any other Python script without special directories or configs

Feature	Railtracks	LangGraph	Google ADK
Python-first, no DSL	✅ Yes	❌ No	✅ Yes
Built-in visualization	✅ Yes	✅ Yes	⚠️ Limited
Simple Running	✅ Yes	✅ Yes	❌ No
LLM-agnostic	✅ Yes	✅ Yes	✅ Yes

Get started with either the quick start or via the docs

Quick Start

Build your first agentic system in just a few steps. Start by building an agent which solves the "how many r's are in Strawberry?" problem.

Step 1: Install the Library

# Core library
pip install railtracks

# [Optional] CLI support for development and visualization
pip install railtracks-cli

Step 2: Define a Tool

import railtracks as rt

# Create your tool
@rt.function_node
def number_of_chars(text: str, character_of_interest: str) -> int:
    return text.count(character_of_interest)

@rt.function_node
def word_count(text: str) -> int:
    return len(text.split())

Step 3: Create your agent (connecting your LLM)

TextAnalyzer = rt.agent_node(
    tool_nodes={number_of_chars, word_count},
    llm=rt.llm.OpenAILLM("gpt-4o"), # use any model you want
    system_message=(
        "You are a text analyzer. You will be given a text and you should utilize the tools available to analyze it."
    ),
)

Step 4: Run Your Application

import asyncio

@rt.session
async def main():
    result = await rt.call(
        TextAnalyzer,
        rt.llm.MessageHistory([
            rt.llm.UserMessage("Hello world! This is a test of the Railtracks framework.")
        ])
    )
    print(result)

asyncio.run(main())

Optional: Visualize the Run

railtracks init
railtracks viz

And just like that, you're up and running. The possibilities are endless.

---

Contributing

See CONTRIBUTING.md for guidelines.