Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.celesto.ai/llms.txt

Use this file to discover all available pages before exploring further.

Agentor is an open-source Python framework for building and deploying long-running AI agents — with tool use, MCP support, A2A protocol, and durable execution built in.
View source on GitHub · Start with Quickstart

​
Quick example

Build an agent, connect tools, and serve it over the A2A protocol in a few lines: 
from agentor import Agentor
from agentor.tools import GetWeatherTool

agent = Agentor(
    name="Weather Agent",
    model="gpt-5-mini",
    tools=[GetWeatherTool()]
)

result = agent.run("What is the weather in London?")
print(result)

# Serve the agent with A2A enabled
agent.serve()
agent.serve() automatically enables the A2A protocol, making your agent discoverable and interoperable with other agents.

​
Start in 5 minutes

Quickstart

Install Agentor and run your first working agent in minutes.

Installation

Set up Python, install Agentor, and configure provider credentials.

​
Explore by topic

Start Here

Install Agentor, run your first agent, and understand the core entry points.

Build Agents

Learn practical agent construction, deployment, tracing, skills, and A2A basics.

Tool Use & MCP

Implement tool calling and MCP servers, then integrate them into agent workflows.

Concepts

Understand architecture, lifecycle, security boundaries, and communication patterns.

Guides

Follow end-to-end workflows for building, streaming, deploying, and observing agents.

API Reference

Dive into class-level and tool-level API details for implementation precision.

First-time builder

Start with quickstart, then move to building agents and custom tools.

Production deployer

Focus on deployment, observability, tracing, and long-running reliability patterns.

Platform integrator

Build MCP servers and A2A-connected agents for broader multi-system integration.
Last modified on May 5, 2026