> For the complete documentation index, see [llms.txt](https://docs.sesori.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sesori.com/get-started/quickstart.md).

# Quickstart

You need the Sesori Bridge on the computer that holds your code, the Sesori app on your phone, and at least one supported AI coding assistant.

{% hint style="info" %}
New to the terminal? Installing and starting the Bridge requires a few commands. If you get stuck, [email us](mailto:contact@sesori.com).
{% endhint %}

## 1. Install the app

* **iOS:** [Download from the App Store](https://apps.apple.com/app/sesori/id6760642500)
* **Android:** [Download from Google Play](https://play.google.com/store/apps/details?id=com.sesori.app)

Open the app and sign in. Use the same Sesori account when you start the Bridge.

More details: [Install the app](/setup/install-the-app.md)

## 2. Install and start the Bridge

{% tabs %}
{% tab title="macOS or Linux" %}

```bash
curl -fsSL https://sesori.com/install.sh | bash
```

{% endtab %}

{% tab title="Windows" %}
Open PowerShell and run:

```powershell
irm https://sesori.com/install.ps1 | iex
```

{% endtab %}
{% endtabs %}

You can also run `npx @sesori/bridge` on a machine with Node.js. It installs or refreshes the Bridge; it does not start it.

```bash
sesori-bridge
```

Choose a sign-in method. GitHub, Google, and Apple authentication open or print a browser URL; email authentication continues in the terminal.

Keep this process running while you use Sesori. The Bridge connects your phone to the assistants and projects on this computer.

More details: [Install and start the Bridge](/setup/set-up-the-bridge.md)

## 3. Connect the app and Bridge

The app and Bridge pair automatically when both use the **same Sesori account**. Confirm that the Bridge indicator in the app turns green.

More details: [Connect the app and Bridge](/setup/connect-the-app.md)

## 4. Choose and install a harness

In Sesori, open **Settings → Harnesses** and choose one of these assistants:

* OpenCode
* Codex
* Cursor
* Claude Code
* Pi
* Oh My Pi
* Hermes Agent

Use **Install runtime** when Sesori offers it. Otherwise, install and authenticate the assistant locally, then refresh its status in Sesori. Compare the options in [Choose a harness](/setup/choose-a-harness.md), then follow [Install a harness](/setup/prepare-your-assistant.md) when local setup is required.

## 5. Create your first session

1. Open a project. If none appears, use **Add Project** to select a folder on your computer.
2. Tap **New session**.
3. Select a **Coding tool** and any available model or agent options.
4. Send a prompt.

The controls inside the session depend on what the selected assistant supports.

More details: [Create your first session](/setup/create-a-session.md)

{% hint style="success" %}
If something does not connect, start with the five [quick checks](/help/troubleshooting.md#quick-checks).
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.sesori.com/get-started/quickstart.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.