Skip to main content
By the end of this guide, your code will start a session on a real Windows machine, capture a native-resolution frame, and send native input — all through the Glasswarp API.
Using n8n? Start at Use with n8n (HTTP Request — no community node). Using Claude, Cursor, or another MCP client? See Connect via MCP.

​
Prerequisites

1

A Windows PC, online and API-enabled

The PC owner installs from Downloads (no account). You pair the tray code and turn on API access. See Install the host.
2

An API key

Create one in the Console. Keys look like gw_live_sk_....
3

Python 3.9+

The SDK is Python. REST works from any language — see the API reference.

​
1. Install the SDK

Add the grounding extra (glasswarp[grounding]) only when you need the Set-of-Mark and ROI image helpers, which pull in Pillow.

​
2. Set your API key

The client reads GLASSWARP_API_KEY automatically. Never hardcode or commit it.

​
3. Run your first session

office-pc is a stand-in. Use gw.list_rigs() to find an online PC with API access enabled — see Pair a PC. Prefer click_target over raw x,y (that path is PyAutoGUI-shaped and brittle).

​
4. Watch it live

Open Console → Sessions → Eye to watch the session at 60fps while your code runs. You’ll see the on-screen “API session active” indicator on the host — that is the owner-consent guardrail, always on.

​
Next steps

Ground your clicks

Click UIA targets instead of guessing pixels.

Build an agent loop

observe → model → act, efficiently.

Launch apps

Spawn and drive Windows applications.

API reference

Every endpoint, with a request builder.