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

# FAQ

> Frequently asked questions about Orca Memory

## General

<AccordionGroup>
  <Accordion title="What is Orca Memory?">
    Orca Memory is a memory plugin for [OpenClaw](https://openclaw.ai). It enables your Claw to remember context across sessions - your preferences, past decisions, code patterns, and project knowledge.
  </Accordion>

  <Accordion title="How does it work with OpenClaw?">
    Orca Memory is an [OpenClaw plugin](https://docs.openclaw.ai/plugin#plugins). Once installed and configured, it:

    * **Auto-Recall**: Injects relevant memories before each AI turn
    * **Auto-Capture**: Stores important information after each turn
    * **Tools**: Provides manual memory management tools to your Claw
  </Accordion>

  <Accordion title="Is my data secure?">
    Yes. All data is encrypted in transit (TLS) and at rest. We use Convex for data storage, which provides enterprise-grade security. For maximum control, you can self-host Orca Memory.
  </Accordion>

  <Accordion title="Can I use Orca Memory offline?">
    The cloud version requires internet connectivity. For offline use, you can self-host Orca Memory on your local network.
  </Accordion>
</AccordionGroup>

## Cloud

<AccordionGroup>
  <Accordion title="How do I get started?">
    1. Sign up at [app.orcamemory.com](https://app.orcamemory.com)
    2. Create a project
    3. Get your API keys (Key ID + API Key)
    4. Install the Orca Memory plugin in OpenClaw
    5. Configure with your credentials

    See the [Quickstart](/cloud/quickstart) for details.
  </Accordion>

  <Accordion title="What happens if I hit my plan limits?">
    On the Free plan, requests beyond the daily limit will be rejected. Consider upgrading to Tide or Abyss for higher limits.
  </Accordion>

  <Accordion title="Can I delete my data?">
    Yes. You can delete individual memories, entire projects, or your account. All data is permanently removed within 30 days per our retention policy.
  </Accordion>

  <Accordion title="Do you offer a free trial of paid plans?">
    New accounts start with a 14-day Tide trial. No credit card required.
  </Accordion>
</AccordionGroup>

## Self-Hosting

<AccordionGroup>
  <Accordion title="What do I need to self-host?">
    * A Convex account (free tier works)
    * Docker and Docker Compose
    * A server with at least 1GB RAM

    See [Requirements](/self-hosting/requirements) for full details.
  </Accordion>

  <Accordion title="Is self-hosting free?">
    The Orca Memory software is open source and free to self-host. You'll only pay for your own infrastructure (hosting, Convex usage if beyond free tier).
  </Accordion>

  <Accordion title="Can I use my own embedding model?">
    Yes. The embeddings service supports sentence-transformer models. Configure it via the `EMBEDDING_MODEL` environment variable. Default is `intfloat/e5-base-v2`.
  </Accordion>

  <Accordion title="How do I update self-hosted Orca Memory?">
    Pull the latest code and rebuild:

    ```bash theme={null}
    git pull origin main
    docker-compose build
    docker-compose up -d
    npx convex deploy
    ```
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="My Claw isn't storing memories">
    Check that:

    1. The plugin is installed and enabled in OpenClaw
    2. Your API URL, Key ID, and API Key are correct
    3. Auto-Capture is enabled (or use tools manually)
    4. Your plan hasn't exceeded its limits
  </Accordion>

  <Accordion title="Auto-Recall isn't working">
    Ensure:

    1. Auto-Recall is enabled in plugin settings
    2. You have existing memories stored
    3. The conversation has enough context for semantic matching
    4. Check `maxRecallResults` isn't set to 0
  </Accordion>

  <Accordion title="Search isn't returning relevant results">
    Semantic search works best with:

    * Descriptive, natural language queries
    * Memories that have clear, detailed content
    * Appropriate tags for filtering

    Try rephrasing your query or lowering the similarity threshold.
  </Accordion>

  <Accordion title="I'm getting rate limited">
    If you're hitting rate limits:

    * Surface (Free): 500K tokens, 5K searches/month
    * Upgrade to Tide or Abyss for higher limits
    * Consider reducing `profileFrequency` to inject less often
  </Accordion>
</AccordionGroup>

## Contact

Still have questions? Reach out:

* **Discord**: [Join our community](https://discord.gg/DptEDf3n)
* **Email**: [support@orcamemory.com](mailto:support@orcamemory.com)
* **GitHub**: [Open an issue](https://github.com/Nebaura-Labs/orcamemory/issues)