Key Concepts at a Glance

TL;DR: RunAgent turns your Python AI agents into multi-language APIs with zero infrastructure headaches. Write once in Python, use everywhere.

The Magic in 4 Bullets

Traditional: Build Everything Yourself

RunAgent: Deploy in One Command

Concept	What It Means	Why It Matters
Entrypoints	Python functions exposed as API endpoints	Your business logic becomes accessible from any language
Tags	Nicknames for your functions (e.g., “chat”, “analyze”)	Clean, memorable API names instead of function names
Streaming	Real-time token delivery as they are generated	Interactive UIs, progress indicators, better UX
Isolation	Secure, containerized execution environments	Security, resource isolation, fast cold starts
SDKs	Language-native clients that feel like local functions	No need to learn REST APIs or WebSocket protocols
Config	`runagent.config.json` defines your agent’s interface	Single source of truth for what your agent can do

Write Python Agent

def chat_agent(message: str) -> str:
    return llm.chat(message)

Deploy with One Command

runagent serve .

Call from Any Language

# Python
result = client.run(message="Hello!")

// JavaScript
const result = await client.run({message: "Hello!"});

// Go
result, _ := client.Run(ctx, map[string]interface{}{"message": "Hello!"})

Built specifically for AI agents, not generic microservices. Handles streaming, state, and agent patterns out of the box.

No Docker, Kubernetes, or cloud configuration needed. Focus on your agent logic, not deployment.

Security, scaling, monitoring, and error handling built-in from day one.

Your Python agent becomes a first-class citizen in every supported language ecosystem.