Skip to main content

​
Prerequisites

  • Python 3.10 or higher
  • An OpenAI API key (or other supported LLM provider)

​
Get started in 3 steps

1

Install

pip install agentor
2

Build an Agent

Create your first agent with just a few lines of code.
from agentor import Agentor

agent = Agentor(
    name="Translator",
    instructions="Translate Spanish to English.",
    model="gpt-5-mini",
)
result = agent.run("Hola, ¿cómo estás?")

Hello, how are you?
3

Add a tool capability

Give your agent the ability to interact with the real world.
from agentor.tools import WeatherAPI
from agentor import Agentor

agent = Agentor(
    name="Weather Agent",
    model="gpt-5-mini",
    tools=[WeatherAPI()]
)
result = agent.run("What's the weather in London?")

​
Observability and tracing

Agentor supports tracing for agent runs and tool calls. Set CELESTO_API_KEY to enable automatic tracing, or enable it explicitly in the agent configuration.

Set up tracing

Follow the step-by-step tracing setup guide.

​
Next steps

Build an Agent

Learn how to build an Agent with tools.

Build an MCP Server

Learn how to add capabilities to your Agent with MCP Servers.

Deploy your Agent

Learn how to deploy your Agent to cloud and access it from your applications.