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

# Introduction

> Autonomous agents that work without you - define in markdown, run on cron, CI/CD, or serverless

<img className="block dark:hidden" src="https://mintcdn.com/agentuse/iaipYT4FIPNTql1X/static/agentuse-logo-word-black.svg?fit=max&auto=format&n=iaipYT4FIPNTql1X&q=85&s=e7763fae824f127eba2cf5e797f082fc" alt="AgentUse Logo" width="480" data-path="static/agentuse-logo-word-black.svg" />

<img className="hidden dark:block" src="https://mintcdn.com/agentuse/iaipYT4FIPNTql1X/static/agentuse-logo-word-white.svg?fit=max&auto=format&n=iaipYT4FIPNTql1X&q=85&s=a7617397878653b5659f38134ff60bd3" alt="AgentUse Logo Dark" width="480" data-path="static/agentuse-logo-word-white.svg" />

## Autonomous Agents That Work Without You

**AgentUse** is a CLI framework for building autonomous AI agents. Define agents in markdown, run via cron, CI/CD, or serverless, and get results without babysitting. No SDK. No flowcharts. Just AI that works while you don't.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get up and running with your first agent in under 5 minutes
  </Card>

  <Card title="Examples" icon="code" href="https://github.com/agentuse/agentuse/tree/main/templates/agents">
    Browse ready-to-use agent examples
  </Card>
</CardGroup>

## Why AgentUse?

### The Problem

AI tools today force you to choose:

* **Interactive copilots** require your constant attention - great for pair programming, but can't run unattended
* **Visual workflow tools** give you drag-and-drop simplicity but create version control nightmares and vendor lock-in
* **SDK-heavy frameworks** offer power but require hundreds of lines of boilerplate just to say "hello world"

### The Solution

AgentUse creates autonomous agents that work without you. Define agents in markdown, run via cron, CI/CD, or serverless, and get results asynchronously.

<AccordionGroup>
  <Accordion title="Runs Unattended">
    Run via cron jobs, CI/CD pipelines, and serverless functions. No babysitting required.
  </Accordion>

  <Accordion title="Version Control Just Works">
    Diff, review, and merge agents like any other code. Your agents are text files that integrate seamlessly with Git.
  </Accordion>

  <Accordion title="No SDK Required">
    If you can write plain English, you can build an agent. No new syntax or programming required.
  </Accordion>

  <Accordion title="Production Ready">
    Built-in retries, streaming, error recovery, and MCP support. Sub-second startup times.
  </Accordion>
</AccordionGroup>

**Copilots assist you. AgentUse agents work for you.**

## Key Features

<Steps>
  <Step title="Autopilot Execution">
    Run agents via cron jobs, CI/CD pipelines, and serverless functions. Sub-second startup times.
  </Step>

  <Step title="Multi-Provider Support">
    Works with Anthropic Claude (including OAuth), OpenAI GPT, OpenRouter, and Amazon Bedrock with flexible API key management.
  </Step>

  <Step title="MCP Integration">
    Connect to any Model Context Protocol server for database, filesystem, and API access.
  </Step>

  <Step title="Sub-Agent Support">
    Build complex workflows by composing multiple specialized agents.
  </Step>
</Steps>

## Try It Now

No API keys needed - run this to see AgentUse in action:

```bash theme={"system"}
npx -y agentuse@latest run https://agentuse.io/hello.agentuse
```

## How It Works

AgentUse agents are markdown files with YAML configuration and plain English instructions:

```yaml theme={"system"}
---
model: anthropic:claude-haiku-4-5
---

You are a helpful assistant.

## Task
Say hello to the user and ask how you can help them today.
```

That's it! Save this as `hello.agentuse` and run:

```bash theme={"system"}
npx -y agentuse@latest run hello.agentuse
```

The agent name is automatically derived from the filename, keeping configuration minimal.

## What Can You Build?

* **MCP-Powered Tools** - Access databases, filesystems, and APIs through MCP servers
* **Multi-Agent Systems** - Compose specialized agents for complex workflows
* **Automation Scripts** - Replace complex bash scripts with intelligent agents
* **Data Processing** - Transform and analyze data with natural language
* **Content Generation** - Create content with consistent voice and style
* **Integration Workflows** - Connect multiple services through MCP protocols