railtracks 1.1.14

The Railtracks Framework for building resilient agentic systems in simple python

Railtracks

Agents in minutes • Zero config • Local visualization • Pure Python

---

✨ What is $${{\color{YellowOrange}\huge\textbf{\textsf{Railtracks}}}}$$?

Easy agent building, for no one but YOU: Create deployable complex agents using simple, Pythonic style interface with natural control flow.

import railtracks as rt

# Define a tool (just a function!)
def get_weather(location: str) -> str:
    return f"It's sunny in {location}!"

# Create an agent with tools
agent = rt.agent_node(
    "Weather Assistant",
    tool_nodes=(rt.function_node(get_weather)),
    llm=rt.llm.OpenAILLM("gpt-4o"),
    system_message="You help users with weather information."
)

# Run it
result = await rt.call(agent, "What's the weather in Paris?")
print(result.text)  # "Based on the current data, it's sunny in Paris!"

That's it. No complex configurations, no learning proprietary syntax. Just Python.

---

🎯 Why Railtracks?

🐍 Pure Python Experience # Write agents like regular functions @rt.function_node def my_tool(text: str) -> str: return process(text) ✅ No YAML, no DSLs, no magic strings ✅ Use your existing debugging tools ✅ IDE autocomplete & type checking	🔧 Tool-First Architecture # Any function becomes a tool agent = rt.agent_node( "Assistant", tool_nodes=(my_tool, api_call) ) ✅ Instant function-to-tool conversion ✅ Seamless API/database integration ✅ MCP protocol support
⚡ Look Familiar? # Smart parallelization built-in # with interface similar to asyncio result = await rt.call(agent, query) ✅ Easy to learn standardized interface ✅ Built-in validation, error handling & retries ✅ Auto-parallelization management	👁️ Transparent by Design railtracks viz # See everything ✅ Real-time execution visualization ✅ Complete execution history ✅ Debug like regular Python code

---

🚀 Quick Start

📦 Installation

🐍 Pure Python Experience # Write agents like regular functions @rt.function_node def my_tool(text: str) -> str: return process(text) ✅ No YAML, no DSLs, no magic strings ✅ Use your existing debugging tools ✅ IDE autocomplete & type checking

🔧 Tool-First Architecture # Any function becomes a tool agent = rt.agent_node( "Assistant", tool_nodes=(my_tool, api_call) ) ✅ Instant function-to-tool conversion ✅ Seamless API/database integration ✅ MCP protocol support

⚡ Look Familiar? # Smart parallelization built-in with interface similar to asyncio result = await rt.call(agent, query) ✅ Easy to learn standardized interface ✅ Built-in validation, error handling & retries ✅ Auto-parallelization management

👁️ Transparent by Design pip install railtracks railtracks-cli ⚡ Your First Agent in 5 Min import railtracks as rt # 1. Create tools (just functions with decorators!) @rt.function_node def count_characters(text: str, character: str) -> int: """Count occurrences of a character in text.""" return text.count(character) @rt.function_node def word_count(text: str) -> int: """Count words in text.""" return len(text.split()) # 2. Build an agent with tools text_analyzer = rt.agent_node( "Text Analyzer", tool_nodes=(count_characters, word_count), llm=rt.llm.OpenAILLM("gpt-4o"), system_message="You analyze text using the available tools." ) # 3. Use it to solve the classic "How many r's in strawberry?" problem @rt.session async def main(): result = await rt.call(text_analyzer, "How many 'r's are in 'strawberry'?") print(result.text) # "There are 3 'r's in 'strawberry'!" # Run it import asyncio asyncio.run(main()) 📊 Visualize Agent in 5 second railtracks init # Setup visualization (one-time) railtracks viz # See your agent in action 🔍 See every step of your agent's execution in real-time 💡 Real-World Examples 🔍 Multi-Agent Research System # Research coordinator that uses specialized agents researcher = rt.agent_node("Researcher", tool_nodes=(web_search, summarize)) analyst = rt.agent_node("Analyst", tool_nodes=(analyze_data, create_charts)) writer = rt.agent_node("Writer", tool_nodes=(draft_report, format_document)) coordinator = rt.agent_node( "Research Coordinator", tool_nodes=(researcher, analyst, writer), # Agents as tools! system_message="Coordinate research tasks between specialists." ) 🔄 Complex Workflows Made Simple # Customer service system with context sharing async def handle_customer_request(query: str): with rt.Session() as session: # Technical support first technical_result = await rt.call(technical_agent, query) # Share context with billing if needed if "billing" in technical_result.text.lower(): session.context["technical_notes"] = technical_result.text billing_result = await rt.call(billing_agent, query) return billing_result return technical_result 🌟 What Makes Railtracks Special? A lightweight agentic LLM framework for building modular, multi-LLM workflows with a focus on simplicity and developer experience. Feature Railtracks LangGraph Google ADK 🐍 Python-first, no DSL ✅ ❌ ✅ 📊 Built-in visualization ✅ ✅ ⚠️ ⚡ Zero setup overhead ✅ ✅ ❌ 🔄 LLM-agnostic ✅ ✅ ✅ 🎯 Pythonic style ✅ ❌ ⚠️ 🔗 Universal LLM Support Switch between providers effortlessly: # OpenAI rt.llm.OpenAILLM("gpt-4o") # Anthropic rt.llm.AnthropicLLM("claude-3-5-sonnet") # Local models rt.llm.OllamaLLM("llama3") Works with OpenAI, Anthropic, Google, Azure, and more! Check out our neatly crafted docs. 🛠️ Powerful Features 📦 Rich Tool Ecosystem Use existing tools or create your own: ✅ Built in Tools RAG, CoT, etc. ✅ Functions → Tools automatically ✅ MCP Integration as client or as server ✅ Agents as Tools → agent cluster 🔍 Built-in Observability Debug and monitor with ease: ✅ Real-time execution graphs ✅ Performance metrics ✅ Error tracking & debugging ✅ Local visualization ✅ Session management ✅ No signup required! 📚 Learn More Documentation Complete guides & API reference Quickstart Up and running in 5 minutes Examples Real-world implementations Discord Get help & share creations Contributing Help make us better 🚀 Ready to Build? pip install railtracks railtracks-cli ✨ Join developers across the world building the future with AI agents You grow, we grow - Railtracks will expand with your ambitions. Made with lots of ❤️ and ☕ by the ◊Railtracks◊ team • Licensed under MIT • Report Bug • Request Feature