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

# Use Elephas Without Sending Anything to the Cloud

> Set up Elephas so your documents and questions stay on your computer: Local AI with Sync off. Plus exactly what still goes online in that setup, and why.

Choose Local AI and leave Personal Sync off. In that setup, your documents, questions, answers and chats stay on your computer. Elephas still goes online for a few account and app tasks, listed below, and none of them carry your content.

## Before you start

* **Local AI needs enough memory and disk space.** Models range from about 1.2 GB to 5.3 GB. See [Choose a local model](/docs/ai-options/choose-a-local-model).
* **Downloads need a connection once.** The first-run models and the Local AI model must be downloaded before you go offline. See [First-run downloads](/docs/getting-started/first-run-downloads).
* **Personal workspace.** In a Team workspace, the Team Owner's AI policy decides which modes are allowed. See [Team AI policy](/docs/teams/team-ai-policy).

## Steps

<Steps>
  <Step title="Set up Local AI">
    Open **Settings › AI**. Under **How Elephas answers**, choose **Local (on this computer)**. Pick a model or keep **Choose for me**, then confirm the download. Wait until the status reads **Local AI ready**. Full steps: [Run Local AI](/docs/ai-options/run-local-ai).
  </Step>

  <Step title="Check that every download is finished">
    Open **Settings › Downloads**. When everything is present, it reads "Everything is downloaded. Elephas works offline."
  </Step>

  <Step title="Leave Personal Sync off">
    Open **Settings › Sync**. If Sync is on, see [Turn off Sync](/docs/sync-and-devices/turn-off-sync). Sync is off unless you turned it on.
  </Step>

  <Step title="Turn off usage reports (optional)">
    Open **Settings › Privacy** and turn off **Send anonymous usage and error reports**. Reports never include your documents or questions, but this stops them too. See [Usage reports](/docs/privacy-and-security/usage-reports).
  </Step>

  <Step title="Check an answer">
    Ask a question. The answer's badge reads **Answered by: This computer**.
  </Step>
</Steps>

The steps are the same on Mac and Windows.

## How it works

### What stays on your computer

**Indexing happens on your computer. Always.** In every mode, reading your files, OCR, the search index and finding passages run locally.

**In Local AI mode, answering does too.** The model runs on your computer, through a local engine that only accepts connections from your own computer. Your question, the passages it reads, your chat history and the answer are not sent to any AI provider. In the app: "Answers are generated on this computer. Nothing is sent anywhere."

### What still goes online, and why

| What | When | What is sent |
| - | - | - |
| **Plan check for Local AI** | Before a Local AI answer, at most once an hour while Elephas is open | A device ID. Never a question, document or answer. |
| **Sign-in** | When you sign in, in your browser | Your sign-in details, to the sign-in service |
| **Plan and device status** | When Elephas starts while you are signed in, and when you open **Plan & Billing** | Account and device information |
| **Update check** | Shortly after Elephas starts, then every 6 hours | A request for the update list. Updates are signed and checked before they install. |
| **Downloads** | First run, setting up Local AI, adding OCR languages, repairing a missing model | Requests for the files |
| **Usage and error reports** | Only if you allow them | Anonymous reports, never your content |
| **Web pages you add** | Only when you add a web page to a Brain | A request to that web page |

With Sync off, nothing is sent to the sync service.

### Working with Wi-Fi off

Turn off your Wi-Fi after Elephas has confirmed your plan, and Local AI still answers from your documents. Elephas keeps a confirmed plan check in memory for up to an hour. After that hour, or after you restart Elephas, it needs to reach the Elephas service again before the next Local AI answer. If it can't, it shows: "Elephas could not confirm your plan right now. Check your connection and try again." Your documents, Brains and chats stay available to browse.

## Troubleshooting

<AccordionGroup>
  <Accordion title="Elephas could not confirm your plan right now">
    Elephas needs to reach the Elephas service about once an hour, and after each restart, to confirm your plan for Local AI. Reconnect briefly, then ask again.
  </Accordion>

  <Accordion title="Local AI isn't ready yet. Check Settings.">
    The model has not finished downloading or setting up. Open **Settings › AI** and check the Local AI status. See [Local AI troubleshooting](/docs/troubleshooting/local-ai-troubleshooting).
  </Accordion>

  <Accordion title="Answers are slow">
    Local models are slower than cloud AI, especially on computers with less memory. A smaller model answers faster. See [Choose a local model](/docs/ai-options/choose-a-local-model).
  </Accordion>
</AccordionGroup>

## Related articles

<CardGroup cols={2}>
  <Card title="Run Local AI" href="/docs/ai-options/run-local-ai" />

  <Card title="What data is sent to AI" href="/docs/privacy-and-security/what-data-is-sent-to-ai" />

  <Card title="Where your data is stored" href="/docs/privacy-and-security/where-your-data-is-stored" />

  <Card title="Usage reports" href="/docs/privacy-and-security/usage-reports" />
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.