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

# Frequently asked questions

> Practical answers about models, memory, embodiment, and operating ngram.

<AccordionGroup>
  <Accordion title="Do I need a GPU?">
    No for hosted inference. You need enough local hardware for your selected model only when running Ollama or another local inference backend. The Entity runtime can use a hosted chat and embedding provider. See [quickstart](/quickstart).
  </Accordion>

  <Accordion title="Do I need a headset?">
    No. Start in a terminal or messaging app. The spatial surface also runs in a desktop browser. Headset features depend on an immersive WebXR session and the capabilities it reports.
  </Accordion>

  <Accordion title="Is a shell a separate agent?">
    A shell is a body and presentation layer. In the canonical `ngram_entity` binding, identity, memory, and reasoning stay with the running Python Entity.
  </Accordion>

  <Accordion title="Can I use a hosted model?">
    Yes. The setup wizard includes hosted providers and a custom compatible endpoint route. A working chat request does not guarantee tool or embedding compatibility; validate those too. See [hosted inference](/deployment/hosted-inference-testing).
  </Accordion>

  <Accordion title="Can I bring an OpenClaw or Hermes harness?">
    The spatial architecture separates bindings from rendering, but v1 does not ship a universal plug-and-play adapter for every external harness. The production continuity path documented here is `ngram_entity`. Use the [protocol guide](/spatial/protocol) to understand the integration boundary.
  </Accordion>

  <Accordion title="Does it remember everything?">
    No. ngram stores several forms of state and selectively retrieves, summarizes, consolidates, and decays memory. Working context is finite. Back up important state and inspect what was actually retained.
  </Accordion>

  <Accordion title="Why is my provider being called while I am not chatting?">
    An always-on Entity can run soma, GEN, autonomous wake, distillation, consolidation, and scheduled automation work. Closing the browser does not stop its worker. See [usage and controls](/guides/usage-and-controls).
  </Accordion>

  <Accordion title="Does disabling autonomy stop all inference?">
    No. Other background paths remain, and the daemon has a legacy initiative path when autonomy is disabled. Stop the process or service when you need a reliable end to requests.
  </Accordion>

  <Accordion title="Can I move an Entity to another machine?">
    Use the portable container and export/verify/recovery workflows. Credentials are provisioned separately. See [persistence](/deployment/persistence).
  </Accordion>

  <Accordion title="What is open source?">
    ngram, including the Python runtime and `ngramAR`, uses the [MIT License](https://github.com/ngramspatial/ngram/blob/main/LICENSE). Model assets and external dependencies can have their own licenses; keep their notices when redistributing them.
  </Accordion>
</AccordionGroup>