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

# FAQ

> Answers to common questions about RemoteAgent.CHAT setup, security, billing, and usage.

<AccordionGroup>
  <Accordion title="Do I need to keep my computer on?">
    Yes. The agent runs as a process on your machine — it is the component that executes your AI runner and processes commands. If your machine is off or the agent process has stopped, the bot will not be able to run tasks.

    For always-on availability, run the agent on a server, a cloud VM, or a machine that stays powered. Use a process supervisor like `pm2` or `systemd` to restart the agent automatically after reboots or crashes.

    ```bash theme={null}
    pm2 start "remoteagent start" --name my-project --cwd /path/to/project
    pm2 startup
    pm2 save
    ```
  </Accordion>

  <Accordion title="Which runner should I choose?">
    Start with `claude-code` — it uses the Claude CLI and gives you full Claude capability. If you already have Claude installed and authenticated, it works with no additional API key.

    If you want the lowest latency and are happy managing an Anthropic API key directly, `claude-sdk` runs in-process with no subprocess overhead.

    If you want a free option with no API key at all, try `opencode` — it supports 75+ providers including GitHub Copilot and local models, and works out of the box with no configuration.

    If you want a free option with Gemini models, try `gemini` — the Google Gemini CLI has a free tier. Note that it is currently in beta.

    If you need multi-model flexibility or want to use local models via Ollama, `aider` is the right choice. It requires Python.

    If you have a custom tool or internal AI gateway, use the `custom` runner.
  </Accordion>

  <Accordion title="Is my API key safe?">
    Yes. Your API key is stored in `~/.remoteagent/agents/{agentId}.json` on your local machine and is **never transmitted to RemoteAgent.CHAT servers**. The agent calls the AI model API directly from your machine. RemoteAgent.CHAT only sees the prompt you sent via Telegram, not the full conversation context or your credentials.

    For additional security, set restrictive permissions on the config files:

    ```bash theme={null}
    chmod 700 ~/.remoteagent
    chmod 600 ~/.remoteagent/agents/*.json
    ```
  </Accordion>

  <Accordion title="Can I use multiple projects?">
    Yes. Run `remoteagent init` in each project directory to register a new agent. Each agent gets a unique ID and appears as a separate entry in the bot and dashboard.

    The number of projects you can register depends on your plan:

    * **Trial / Pro** — unlimited projects
    * **Solo** — 1 project

    When multiple agents are online, commands go to the currently active project. Send `/projects` to see the list and switch.
  </Accordion>

  <Accordion title="What happens when my trial ends?">
    When the 14-day trial expires, your agents stop accepting commands and the bot notifies you. Your data — agents, session history, config files — is preserved in full.

    To reactivate, choose any paid plan from the dashboard or via the link in the bot's trial expiry message. Your agents come back online within 30 seconds of payment confirmation, automatically.
  </Accordion>

  <Accordion title="Can I self-host RemoteAgent.CHAT?">
    Not currently. The relay infrastructure runs on RemoteAgent.CHAT's managed stack. The relay is designed to be transparent — it does not inspect your code or store sensitive data beyond a prompt preview. The agent package itself runs entirely on your machine.
  </Accordion>

  <Accordion title="What if my agent goes offline?">
    The bot sends you a Telegram notification immediately when an agent disconnects. The notification includes the project name and a timestamp.

    To bring the agent back online, run `remoteagent start` in your project directory, or by name: `remoteagent start "project-name"`.

    To prevent unplanned downtime, run the agent under a process supervisor that restarts it automatically. See [Offline alerts](/bot/offline-alerts) for setup examples.

    Offline alerts are available on all plans.
  </Accordion>

  <Accordion title="How do I update the agent?">
    Run the reinstall command — it updates to the latest version and restarts any running agents automatically:

    ```bash theme={null}
    remoteagent reinstall
    ```

    Your existing config files and paired agents continue to work after an update.
  </Accordion>

  <Accordion title="Can multiple Telegram users control the same agent?">
    Not currently. Only the account owner's Telegram user can send commands to agents.
  </Accordion>

  <Accordion title="How do I revoke access to a paired agent?">
    Delete the agent from the [dashboard](https://remoteagent.chat/dashboard). This immediately invalidates the agent's credentials — it will no longer be able to receive commands even if the process is still running locally.

    To fully clean up, also stop the agent process on your machine:

    ```bash theme={null}
    remoteagent remove "project-name"
    ```
  </Accordion>

  <Accordion title="What data does RemoteAgent.CHAT store?">
    RemoteAgent.CHAT stores:

    * Your Telegram user ID and username
    * Your plan and billing status
    * Agent metadata: project name, last-seen timestamp, online/offline status
    * Session records: start time, end time, status, and the first 200 characters of your prompt

    RemoteAgent.CHAT does not store:

    * Your API keys
    * Your source code
    * Full prompt or response content
    * File contents processed by the AI runner
  </Accordion>

  <Accordion title="Does RemoteAgent.CHAT work on Windows?">
    The agent binary runs on Windows via **WSL 2** (Windows Subsystem for Linux). Install WSL 2 and run the installer from within the WSL environment — no Node.js required.

    Native Windows support (PowerShell/CMD) is not officially tested or guaranteed. WSL 2 is the recommended path for Windows users.
  </Accordion>
</AccordionGroup>