> ## 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.

# Frequently Asked Questions

> Common questions about RunAgent

## General Questions

<AccordionGroup>
  <Accordion title="What is RunAgent?">
    RunAgent is a platform for deploying AI agents to production. It provides:

    * Framework-agnostic deployment
    * Automatic scaling and monitoring
    * Simple CLI and SDK interfaces
    * Support for all major AI frameworks

    Think of it as "Vercel for AI agents" - deploy with one command and let us handle the infrastructure.
  </Accordion>

  <Accordion title="Which AI frameworks are supported?">
    Currently supported:

    * LangGraph
    * CrewAI
    * Agno
    * Letta
    * Custom Python frameworks

    Coming soon:

    * AutoGen
    * BabyAGI
    * AgentGPT

    You can use any Python-based framework with our custom framework option.
  </Accordion>

  <Accordion title="How does pricing work?">
    **Local deployment**: Free forever

    **Cloud deployment** (coming soon):

    * Free tier: 1,000 requests/month
    * Pro: \$29/month for 50,000 requests
    * Enterprise: Custom pricing

    See [pricing page](https://run-agent.ai/pricing) for details.
  </Accordion>
</AccordionGroup>

## Getting Started

<AccordionGroup>
  <Accordion title="How do I install RunAgent?">
    Simply use pip:

    ```bash theme={null}
    pip install runagent
    ```

    For development with all dependencies:

    ```bash theme={null}
    pip install "runagent[dev]"
    ```
  </Accordion>

  <Accordion title="Do I need to rewrite my existing agent?">
    No! RunAgent works with your existing code. Just:

    1. Add a `runagent.config.json` file
    2. Define your entrypoints
    3. Deploy

    Your agent logic remains unchanged.
  </Accordion>

  <Accordion title="What are entrypoints?">
    Entrypoints are functions RunAgent calls to interact with your agent:

    ```python theme={null}
    # Standard entrypoint
    def invoke(input_data: dict) -> dict:
        return {"result": "processed"}

    # Streaming entrypoint
    def stream(input_data: dict):
        for chunk in process():
            yield chunk
    ```
  </Accordion>
</AccordionGroup>

## Technical Questions

<AccordionGroup>
  <Accordion title="What Python versions are supported?">
    RunAgent supports Python 3.8 and above:

    * Python 3.8
    * Python 3.9
    * Python 3.10
    * Python 3.11
    * Python 3.12
  </Accordion>

  <Accordion title="Can I use custom dependencies?">
    Yes! Add any dependencies to your `requirements.txt`:

    ```txt theme={null}
    openai>=1.0.0
    requests>=2.31.0
    pandas>=2.0.0
    your-custom-package>=1.0.0
    ```

    RunAgent will install them during deployment.
  </Accordion>

  <Accordion title="How do I handle secrets and API keys?">
    **Local development**: Use `.env` files

    ```bash theme={null}
    OPENAI_API_KEY=sk-...
    DATABASE_URL=postgresql://...
    ```

    **Production**: Set in deployment configuration

    ```bash theme={null}
    runagent deploy . --env OPENAI_API_KEY=$OPENAI_API_KEY
    ```

    Secrets are encrypted at rest and never logged.
  </Accordion>

  <Accordion title="What are the resource limits?">
    **Default limits**:

    * Memory: 512MB (configurable up to 8GB)
    * Timeout: 30 seconds (configurable up to 900s)
    * Payload size: 10MB
    * Concurrent requests: Based on plan

    Configure in `runagent.config.json`:

    ```json theme={null}
    {
      "deployment": {
        "memory": "2GB",
        "timeout": 120
      }
    }
    ```
  </Accordion>
</AccordionGroup>

## Deployment Questions

<AccordionGroup>
  <Accordion title="What's the difference between local and cloud deployment?">
    **Local deployment**:

    * Runs on your machine
    * Free forever
    * Good for development and testing
    * Requires your machine to be running

    **Cloud deployment**:

    * Runs on RunAgent infrastructure
    * Auto-scaling and high availability
    * Monitoring and logging included
    * Accessible from anywhere
  </Accordion>

  <Accordion title="How do I update a deployed agent?">
    Simply deploy again with the same name:

    ```bash theme={null}
    # Updates existing deployment
    runagent deploy . --name my-agent
    ```

    RunAgent handles:

    * Zero-downtime updates
    * Automatic rollback on failure
    * Version history
  </Accordion>

  <Accordion title="Can I deploy multiple versions?">
    Yes! Use different names or environments:

    ```bash theme={null}
    # Production version
    runagent deploy . --name agent-prod --env production

    # Staging version
    runagent deploy . --name agent-staging --env staging

    # Development version
    runagent deploy . --name agent-dev --env development
    ```
  </Accordion>
</AccordionGroup>

## SDK Questions

<AccordionGroup>
  <Accordion title="Which languages have SDKs?">
    **Available now**:

    * Python

    **Coming soon**:

    * JavaScript/TypeScript (Q2 2024)
    * Rust (Q2 2024)
    * Go (Q3 2024)

    You can always use the REST API directly from any language.
  </Accordion>

  <Accordion title="How do I handle streaming responses?">
    **Python SDK**:

    ```python theme={null}
    for chunk in client.run_generic_stream(input_data):
        print(chunk, end="", flush=True)
    ```

    **Direct API**:
    Use Server-Sent Events (SSE) with appropriate client library.
  </Accordion>

  <Accordion title="Is the SDK thread-safe?">
    Yes, the SDK clients are thread-safe. You can:

    * Share a client instance across threads
    * Use in async contexts with AsyncRunAgentClient
    * Handle concurrent requests
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="My agent works locally but fails when deployed">
    Common causes:

    1. **Missing environment variables** - Check all are set
    2. **File path issues** - Use relative paths
    3. **Dependency versions** - Pin specific versions
    4. **Resource limits** - Increase memory/timeout

    Debug with:

    ```bash theme={null}
    runagent logs <deployment-id>
    ```
  </Accordion>

  <Accordion title="How do I debug performance issues?">
    1. **Add logging** to identify slow operations
    2. **Use profiling** to find bottlenecks
    3. **Check logs** for errors or warnings
    4. **Monitor metrics** (coming soon)

    ```python theme={null}
    import time
    start = time.time()
    # operation
    print(f"Took {time.time() - start}s")
    ```
  </Accordion>
</AccordionGroup>

## Best Practices

<AccordionGroup>
  <Accordion title="How should I structure my agent project?">
    Recommended structure:

    ```
    my-agent/
    ├── agent.py           # Main agent code
    ├── utils/             # Helper functions
    ├── prompts/           # Prompt templates
    ├── tests/             # Unit tests
    ├── runagent.config.json
    ├── requirements.txt
    ├── .env.example
    └── README.md
    ```
  </Accordion>

  <Accordion title="Should I use sync or async?">
    **Use sync when**:

    * Simple request/response
    * No concurrent operations
    * Easier to debug

    **Use async when**:

    * Multiple API calls
    * I/O intensive operations
    * Need better performance
  </Accordion>
</AccordionGroup>

## Community & Support

<AccordionGroup>
  <Accordion title="How do I get help?">
    1. **Documentation**: [docs.run-agent.ai](https://docs.run-agent.ai)
    2. **Discord**: [discord.gg/runagent](https://discord.gg/runagent)
    3. **GitHub Issues**: For bugs and features
    4. **Email**: [support@run-agent.ai](mailto:support@run-agent.ai) for critical issues
  </Accordion>

  <Accordion title="Can I contribute to RunAgent?">
    Yes! We welcome contributions:

    * Code contributions via GitHub
    * Documentation improvements
    * Bug reports and feature requests
    * Community SDKs and templates

    See our [contributing guide](https://github.com/runagent-dev/runagent/CONTRIBUTING.md).
  </Accordion>

  <Accordion title="Is RunAgent open source?">
    The RunAgent CLI and SDKs are open source (MIT license). The deployment infrastructure is proprietary but offers a generous free tier.
  </Accordion>
</AccordionGroup>

## Still Have Questions?

<CardGroup cols={2}>
  <Card title="Ask on Discord" icon="discord">
    Get help from the community

    [Join Discord →](https://discord.gg/runagent)
  </Card>

  <Card title="Contact Support" icon="envelope">
    For account or billing questions

    [Email Us →](mailto:support@run-agent.ai)
  </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>