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

# Agents

> Learn about Agno Agents and how they work.

**Agents are AI programs where a language model controls the flow of execution.**

The core of an Agent is a model using tools in a loop, guided by instructions:

* **Model:** controls the flow of execution. It decides whether to reason, act or respond.
* **Instructions:** program the Agent, teaching it how to use tools and respond.
* **Tools:** enable an Agent to take actions and interact with external systems.

Agents also have memory, knowledge, storage and the ability to reason:

* **Memory:** gives Agents the ability to store and recall information from previous interactions, allowing them to learn and improve their responses.
* **Storage:** is used by Agents to save session history and state in a database. Model APIs are stateless and storage makes Agents stateful, enabling multi-turn conversations.
* **Knowledge:** is domain-specific information the Agent can **search at runtime** to provide better responses (RAG). Knowledge is stored in a vector database and this search at runtime pattern is known as **Agentic RAG** or **Agentic Search**.
* **Reasoning:** enables Agents to "think" before responding and "analyze" the results of their actions before responding, this improves reliability and quality of responses.

<Tip>
  If this is your first time using Agno, [start here](/introduction/quickstart) before diving into advanced concepts.
</Tip>

## Guides

Learn how to build, run and manage your Agents using the following guides.

<CardGroup cols={3}>
  <Card title="Building Agents" icon="wrench" iconType="duotone" href="/concepts/agents/building-agents">
    Learn how to run your agents.
  </Card>

  <Card title="Running Agents" icon="user-robot" iconType="duotone" href="/concepts/agents/running-agents">
    Learn how to run your agents.
  </Card>

  <Card title="Debugging Agents" icon="bug" iconType="duotone" href="/concepts/agents/debugging-agents">
    Learn how to debug and troubleshoot your agents.
  </Card>

  <Card title="Agent Sessions" icon="comments" iconType="duotone" href="/concepts/agents/sessions">
    Learn about agent sessions.
  </Card>

  <Card title="Input & Output" icon="fire" iconType="duotone" href="/concepts/agents/input-output">
    Learn about input and output for agents.
  </Card>

  <Card title="Context Engineering" icon="file-lines" iconType="duotone" href="/concepts/agents/context">
    Learn about context engineering.
  </Card>

  <Card title="Dependencies" icon="brackets-curly" iconType="duotone" href="/concepts/agents/dependencies">
    Learn about dependency injection in your agent's context.
  </Card>

  <Card title="Agent State" icon="crystal-ball" iconType="duotone" href="/concepts/agents/state">
    Learn about managing agent state.
  </Card>

  <Card title="Agent Storage" icon="database" iconType="duotone" href="/concepts/agents/storage">
    Learn about session storage.
  </Card>

  <Card title="Memory" icon="head-side-brain" iconType="duotone" href="/concepts/agents/memory">
    Learn about adding memory to your agents.
  </Card>

  <Card title="Knowledge" icon="books" iconType="duotone" href="/concepts/agents/knowledge">
    Learn about knowledge in agents.
  </Card>

  <Card title="Tools" icon="wrench" iconType="duotone" href="/concepts/agents/tools">
    Learn about adding tools to your agents.
  </Card>

  <Card title="Agent Metrics" icon="chart-line" iconType="duotone" href="/concepts/agents/metrics">
    Learn how to track agent metrics.
  </Card>

  <Card title="Pre-hooks & Post-hooks" icon="link" iconType="duotone" href="/concepts/agents/pre-hooks-and-post-hooks">
    Learn about pre-hooks and post-hooks for agents.
  </Card>

  <Card title="Guardrails" icon="shield-check" iconType="duotone" href="/concepts/agents/guardrails/overview">
    Learn about implementing guardrails for your agents.
  </Card>
</CardGroup>

## Developer Resources

* View the [Agent schema](/reference/agents/agent)
* View [Cookbook](https://github.com/agno-agi/agno/tree/main/cookbook/agents/README.md)