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

# FAQ

> Frequently asked questions about FERAL — what it is, how it works, privacy, models, and contributing.

## General

<AccordionGroup>
  <Accordion title="What is FERAL?">
    FERAL is a local-first AI runtime that coordinates tools, memory, channels, and device actions from one brain process.

    It can run only on your machine, or integrate with cloud providers depending on your chosen setup.
  </Accordion>

  <Accordion title="How is FERAL different from ChatGPT or Siri?">
    |                 | ChatGPT / Siri           | FERAL                                             |
    | --------------- | ------------------------ | ------------------------------------------------- |
    | **Runs where**  | Their cloud servers      | Your machine                                      |
    | **Memory**      | Forgets between sessions | 4-tier persistent memory + knowledge graph        |
    | **Devices**     | None (or limited)        | Wristbands, glasses, smart home, robots, computer |
    | **Proactive**   | No — waits for prompts   | Yes — watches context and acts                    |
    | **Voice**       | 1-2s cloud latency       | Sub-200ms, wake word, interrupt-and-resume        |
    | **Privacy**     | Data sent to cloud       | Everything stays local                            |
    | **Open source** | No                       | Yes — Apache 2.0                                  |
  </Accordion>

  <Accordion title="How is FERAL different from Open Interpreter or other agent frameworks?">
    FERAL focuses on operational orchestration: one runtime for chat, tools, memory, pairing, channels, and device control paths. It is not only a terminal code assistant.
  </Accordion>
</AccordionGroup>

## Privacy & Security

<AccordionGroup>
  <Accordion title="How do I pair from Anywhere (outside my WiFi)?">
    Choose **Anywhere** during setup. FERAL tries to enable remote access automatically.
    If setup reports a tunnel error, run:

    ```bash theme={null}
    feral access remote-up
    ```

    This enables remote pairing through Tailscale Funnel. Check status with:

    ```bash theme={null}
    feral access status
    ```
  </Accordion>

  <Accordion title="What data leaves my machine?">
    **Only LLM API calls** — and only if you choose a cloud provider (Anthropic, OpenAI, etc.). The text of your query is sent to the provider for inference.

    Everything else stays local:

    * Health data from wearables
    * Memory and knowledge graph
    * Smart-home commands
    * Screen captures
    * Voice audio (processed locally when using Whisper)

    If you use **Ollama** (local models), nothing leaves your machine at all.
  </Accordion>

  <Accordion title="How are my API keys stored?">
    Keys are stored in `~/.feral/credentials.enc`, encrypted with ChaCha20-Poly1305 (AEAD) and a key derived from your master passphrase via Argon2id. The derived key is cached in your OS keychain so the vault unlocks transparently. The vault decrypts in memory only while FERAL is running and the raw values are never shown to the LLM — credentials are injected at the HTTP layer at request time. See [Configuration](/getting-started/configuration) for details.
  </Accordion>

  <Accordion title="Can FERAL access my screen and files?">
    Only if you enable it. Computer-use skills (screen capture, browser automation, file operations) are gated by your **autonomy mode** — set this in **Settings → Autonomy** in the WebUI (the picker writes to `~/.feral/settings.json` under `security.autonomy_mode`). In `strict` mode every file or screen action requires explicit approval; in `hybrid` (default) destructive or `dangerous`-tier actions still require approval; in `loose` everything auto-runs. macOS additionally enforces native TCC permission prompts (Screen Recording, Accessibility) before the brain can start a screen-capture loop.
  </Accordion>
</AccordionGroup>

## Models & Providers

<AccordionGroup>
  <Accordion title="Which LLM models are supported?">
    FERAL supports multiple cloud and local providers. The exact live catalog can change by release and provider API.

    For current provider/model behavior, check Settings in the running dashboard or the provider docs in this site.
  </Accordion>

  <Accordion title="Can I use FERAL without internet (fully offline)?">
    Yes. Use **Ollama** as your LLM provider with a locally downloaded model:

    ```bash theme={null}
    ollama pull llama3:70b
    export FERAL_LLM_PROVIDER=ollama
    export FERAL_LLM_MODEL=llama3:70b
    feral start
    ```

    Combine with `FERAL_VOICE_PROVIDER=whisper_local` for offline voice. All hardware, memory, and smart-home features work offline by default.
  </Accordion>

  <Accordion title="Can I switch models mid-conversation?">
    Yes. Use the dashboard settings or send a command:

    ```
    > Switch to Claude Sonnet for this conversation
    ```

    The brain swaps the active provider while preserving conversation context and memory.
  </Accordion>
</AccordionGroup>

## Hardware

<AccordionGroup>
  <Accordion title="Which wristband does FERAL support?">
    FERAL ships with a BLE adapter for its reference wristband (PPG-based, streaming HR, SpO2, skin temp). It also integrates with **Whoop** and **Oura Ring** via their APIs. Any BLE wearable that exposes standard GATT health services can be adapted. See [Wristband](/hardware/wristband).
  </Accordion>

  <Accordion title="Do I need special hardware to use FERAL?">
    No. Hardware integrations are optional. FERAL works as a powerful AI assistant on just your computer — with memory, voice, computer-use, and all software integrations. Hardware extends it into the physical world.
  </Accordion>
</AccordionGroup>

## Development

<AccordionGroup>
  <Accordion title="Is FERAL production-ready?">
    FERAL is in active development. The core brain, memory system, voice pipeline, and hardware mesh are functional. It is suitable for personal use and development. We don't recommend it for production deployments serving multiple users — yet.
  </Accordion>

  <Accordion title="How do I contribute?">
    ```bash theme={null}
    git clone https://github.com/FERAL-AI/FERAL-AI.git && cd FERAL-AI
    cd feral-core && pip install -e ".[llm,dev]"
    cd ../feral-client-v2 && npm install && npm run dev
    ```

    Read the [CONTRIBUTING.md](https://github.com/FERAL-AI/FERAL-AI/blob/main/CONTRIBUTING.md) for coding standards, PR guidelines, and architecture docs. Issues labeled `good first issue` are a great starting point.
  </Accordion>

  <Accordion title="What license is FERAL under?">
    Apache 2.0. You can use, modify, and distribute FERAL freely, including in commercial products, as long as you include the license notice.
  </Accordion>

  <Accordion title="Can I build commercial products on FERAL?">
    Yes. The Apache 2.0 license explicitly allows commercial use. You can build products, services, or integrations on top of FERAL without restrictions beyond license attribution.
  </Accordion>
</AccordionGroup>