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

# Installation

> Platform requirements and step-by-step instructions for installing Synti on macOS, Windows, and Linux.

Synti is a native desktop app you download and install on your own machine. This page covers the supported platforms, how to install using either the official installers or the install script, and what to expect on first launch.

<Note>
  Synti is a commercial, proprietary application. You install it from official installers (`.dmg`, `.exe`, or Linux AppImage) or the install script — there is no public source repository to clone.
</Note>

## Platform requirements

| Platform | Architecture          | Minimum OS        | Package  |
| -------- | --------------------- | ----------------- | -------- |
| macOS    | Apple Silicon (arm64) | macOS 11          | `.dmg`   |
| Windows  | x64                   | Windows 10        | `.exe`   |
| Linux    | x64                   | — (FUSE required) | AppImage |

<Info>
  The current release line does not ship an Intel (x86\_64) macOS build — Synti requires an Apple Silicon Mac. On Linux, the AppImage needs FUSE to run.
</Info>

## Install with the script

The quickest way to install and stay up to date is the install script. It downloads the correct build for your platform and puts Synti in the right place.

<CodeGroup>
  ```bash macOS / Linux theme={null}
  curl -fsSL https://synti.co/install.sh | bash
  ```

  ```powershell Windows (PowerShell) theme={null}
  irm https://synti.co/install.ps1 | iex
  ```
</CodeGroup>

## Install manually

Prefer to download and run the installer yourself? Choose your platform below.

<Tabs>
  <Tab title="macOS">
    <Steps>
      <Step title="Download the disk image">
        Get the Apple Silicon `.dmg` from the [download page](https://synti.co/download).
      </Step>

      <Step title="Install the app">
        Open the `.dmg` and drag **Synti** into your **Applications** folder.
      </Step>

      <Step title="Launch it">
        Open Synti from Applications or Spotlight. The first time you open it, macOS may ask you to confirm — Synti is signed and notarized under the bundle id `co.synti.app`.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Windows">
    <Steps>
      <Step title="Download the installer">
        Get the x64 `.exe` from the [download page](https://synti.co/download).
      </Step>

      <Step title="Run the installer">
        Double-click the `.exe` and follow the prompts. Synti installs per-user and creates Start menu and desktop shortcuts.
      </Step>

      <Step title="Launch it">
        Open Synti from the Start menu or its shortcut.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Linux">
    <Steps>
      <Step title="Install FUSE">
        The AppImage needs FUSE. On Debian/Ubuntu run `sudo apt install fuse libfuse2`; on Fedora run `sudo dnf install fuse fuse-libs`.
      </Step>

      <Step title="Download the AppImage">
        Get the x64 AppImage from the [download page](https://synti.co/download).
      </Step>

      <Step title="Make it executable and run it">
        ```bash theme={null}
        chmod +x Synti-x64.AppImage
        ./Synti-x64.AppImage
        ```
      </Step>
    </Steps>
  </Tab>
</Tabs>

## First launch

The first time Synti opens, a setup wizard walks you through the initial configuration:

* **Connect a model provider.** Anthropic is the default; you can also connect OpenAI, Google, OpenRouter, Groq, Mistral, xAI, or any OpenAI-compatible endpoint. Provider credentials are encrypted on disk.
* **Create your first workspace.** Workspaces isolate conversations, sources, and settings for different projects.
* **Set a working directory (optional).** Point the agent at a project folder so it can read and edit files right away — see [Working directory](/core-concepts/working-directory).

Everything Synti stores locally — configuration, encrypted credentials, and conversation history — lives under `~/.synti`.

<Tip>
  Once you're set up, start with a read-only [Explore](/core-concepts/permissions) conversation to get a feel for how the agent works before granting it edit or execute access.
</Tip>

## Where to go next

<CardGroup cols={2}>
  <Card title="Conversations" icon="comments" href="/core-concepts/conversations">
    Organize your work as an inbox of resumable sessions.
  </Card>

  <Card title="Permissions" icon="shield-halved" href="/core-concepts/permissions">
    Choose how much the agent is allowed to do.
  </Card>
</CardGroup>