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

# Frameworks Overview

> Deploy agents built with any AI framework

## Supported Frameworks

RunAgent is designed to work with any AI agent framework. We provide first-class support for popular frameworks while allowing custom implementations.

<CardGroup cols={2}>
  <Card title="LangGraph" icon="diagram-project" href="/frameworks/langgraph">
    Build stateful, multi-step agents with graph-based workflows
  </Card>

  <Card title="CrewAI" icon="users" href="/frameworks/crewai">
    Create multi-agent systems with role-based collaboration
  </Card>

  <Card title="Agno" icon="brain" href="/frameworks/agno">
    Develop agents with built-in memory and reasoning
  </Card>

  <Card title="Letta" icon="message" href="/frameworks/letta">
    Build conversational agents with long-term memory
  </Card>

  <Card title="LangChain" icon="link" href="/frameworks/langchain">
    Orchestrate LLM chains into sophisticated workflows
  </Card>

  <Card title="LlamaIndex" icon="list" href="/frameworks/llamaindex">
    Build context-aware document indices for LLM retrieval
  </Card>
</CardGroup>

## Quick Start Examples

<Tabs>
  <Tab title="LangGraph">
    ```bash theme={null}
    runagent init my-agent --framework langgraph
    cd my-agent
    # Edit agents.py with your LangGraph logic
    runagent serve .
    ```
  </Tab>

  <Tab title="CrewAI">
    ```bash theme={null}
    runagent init my-crew --framework crewai
    cd my-crew
    # Define your crew in crew.py
    runagent serve .
    ```
  </Tab>

  <Tab title="Custom">
    ```bash theme={null}
    runagent init my-custom --framework custom
    cd my-custom
    # Implement your agent logic
    runagent serve .
    ```
  </Tab>
</Tabs>

## Framework Integration

All frameworks integrate with RunAgent through:

1. **Standardized Entrypoints**: Define how to invoke your agent
2. **Configuration**: Specify framework in `runagent.config.json`
3. **Environment Management**: Handle API keys and settings
4. **Deployment**: Same process regardless of framework

## Best Practices by Framework

<AccordionGroup>
  <Accordion title="LangGraph Best Practices">
    * Keep graphs simple and readable
    * Use appropriate state persistence
    * Handle edge cases in transitions
    * Test each node independently
  </Accordion>

  <Accordion title="CrewAI Best Practices">
    * Define clear agent roles
    * Minimize agent dependencies
    * Use appropriate delegation patterns
    * Monitor inter-agent communication
  </Accordion>

  <Accordion title="Custom Framework Best Practices">
    * Follow RunAgent conventions
    * Implement proper error handling
    * Document your approach
    * Consider open-sourcing if general-purpose
  </Accordion>
</AccordionGroup>

## Migration Between Frameworks

RunAgent makes it easy to switch frameworks:

1. **Keep business logic separate** from framework code
2. **Use consistent interfaces** for inputs/outputs
3. **Test thoroughly** after migration
4. **Update configuration** in `runagent.config.json`

## Community Frameworks

We're always adding support for new frameworks. Coming soon:

* AutoGen
* BabyAGI
* AgentGPT
* Custom community frameworks

## Contributing Framework Support

Want to add support for a new framework?

1. Check our [contribution guidelines](https://github.com/runagent-dev/runagent/contribute)
2. Create a template for the framework
3. Add documentation
4. Submit a pull request

## Next Steps

<CardGroup cols={2}>
  <Card title="LangGraph Guide" icon="diagram-project" href="/frameworks/langgraph">
    Build your first LangGraph agent
  </Card>

  <Card title="CrewAI Guide" icon="users" href="/frameworks/crewai">
    Create a multi-agent crew
  </Card>
</CardGroup>

<Card title="Still have a question?" icon="circle-question" href="/components/columns">
  * Join our [Discord Community](https://discord.gg/Q9P9AdHVHz)
  * Email us: [hi@run-agent.ai](mailto:hi@run-agent.ai)
  * Follow us on [X](https://x.com/run_agent)
  * New here? [Sign up](https://run-agent.ai/dashboard)
</Card>