> ## 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: Python framework for long-running AI agents

> Agentor is an open-source Python framework for building, deploying, and operating long-running AI agents with tool use, MCP, and the A2A protocol.

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.

<Info>
  [View source on GitHub](https://github.com/CelestoAI/agentor) · [Start with Quickstart](/agentor/quickstart)
</Info>

## Quick example

Build an agent, connect tools, and serve it over the A2A protocol in a few lines:

```python theme={null}
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()
```

<Tip>
  `agent.serve()` automatically enables the A2A protocol, making your agent discoverable and interoperable with other agents.
</Tip>

## Start in 5 minutes

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/agentor/quickstart">
    Install Agentor and run your first working agent in minutes.
  </Card>

  <Card title="Installation" icon="download" href="/agentor/installation">
    Set up Python, install Agentor, and configure provider credentials.
  </Card>
</CardGroup>

## Explore by topic

<CardGroup cols={2}>
  <Card title="Start Here" icon="rocket" href="/agentor/quickstart">
    Install Agentor, run your first agent, and understand the core entry points.
  </Card>

  <Card title="Build Agents" icon="robot" href="/agentor/agents-api">
    Learn practical agent construction, deployment, tracing, skills, and A2A basics.
  </Card>

  <Card title="Tool Use & MCP" icon="screwdriver-wrench" href="/agentor/tools/overview">
    Implement tool calling and MCP servers, then integrate them into agent workflows.
  </Card>

  <Card title="Concepts" icon="lightbulb" href="/agentor/concepts/agents">
    Understand architecture, lifecycle, security boundaries, and communication patterns.
  </Card>

  <Card title="Guides" icon="map" href="/agentor/guides/building-agents">
    Follow end-to-end workflows for building, streaming, deploying, and observing agents.
  </Card>

  <Card title="API Reference" icon="code" href="/agentor/api/agentor">
    Dive into class-level and tool-level API details for implementation precision.
  </Card>
</CardGroup>

## Recommended paths

<CardGroup cols={3}>
  <Card title="First-time builder" icon="bolt" href="/agentor/quickstart">
    Start with quickstart, then move to building agents and custom tools.
  </Card>

  <Card title="Production deployer" icon="cloud" href="/agentor/guides/deployment">
    Focus on deployment, observability, tracing, and long-running reliability patterns.
  </Card>

  <Card title="Platform integrator" icon="plug" href="/agentor/guides/mcp-servers">
    Build MCP servers and A2A-connected agents for broader multi-system integration.
  </Card>
</CardGroup>