> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# What are Agents?

> Agents are AI programs that use tools to accomplish tasks.

Agents are a stateful control loop around a stateless model. The model reasons and calls tools in a loop, guided by instructions. Add memory, knowledge, storage, human-in-the-loop, and guardrails as needed.

## Guides

<CardGroup cols={3}>
  <Card title="Build Agents" icon="wrench" iconType="duotone" href="/agents/building-agents">
    Create agents with tools and instructions.
  </Card>

  <Card title="Run Agents" icon="user-robot" iconType="duotone" href="/agents/running-agents">
    Execute agents and handle responses.
  </Card>

  <Card title="Debug Agents" icon="bug" iconType="duotone" href="/agents/debugging-agents">
    Inspect and troubleshoot agent behavior.
  </Card>
</CardGroup>

## Beyond Single Agents

| Abstraction                         | What it does                                                   |
| ----------------------------------- | -------------------------------------------------------------- |
| [**Team**](/teams/overview)         | Agents that work together                                      |
| [**Workflow**](/workflows/overview) | Orchestrate agents, teams, and functions through defined steps |

## Agents from External Frameworks

Agno also serves agents built with the **Claude Agent SDK**, **LangGraph**, and **DSPy** through the same AgentOS runtime. See [Multi-Framework Support](/agent-os/multi-framework/overview) to wrap an external agent in `ClaudeAgent`, `LangGraphAgent`, or `DSPyAgent` and register it with `AgentOS(agents=[...])` alongside native ones.

## Resources

* [Examples](/cookbook/agents/overview)
* [Reference](/reference/agents/agent)