Getting Started

Record browser interactions and get automation code. This guide will walk you through installation, capturing your first interaction, and generating reusable code.

Installation

Install the Chrome Extension

Download and install the InverseUI Chrome extension to start capturing UI interactions:

  1. Download the extension from GitHub
  2. Unzip the downloaded file
  3. Open Chrome and go to chrome://extensions
  4. Enable "Developer mode" in the top right corner
  5. Click "Load unpacked" and select the unzipped folder
  6. Sign in with your Google account

Once installed, you'll see the InverseUI icon in your browser toolbar. Click it to start recording your first interaction.

First Project

Let's capture your first UI interaction and generate automation code.

1. Start Recording

Click the InverseUI extension icon and perform any actions you want to automate:

  1. Click the InverseUI extension icon
  2. Select "Start Recording"
  3. Perform any actions in the browser (clicks, typing, navigation, etc.)
  4. Click "Stop Recording" when you're done

2. Review Recording

After recording, InverseUI captures all your interactions:

Actions Captured

All clicks, inputs, and navigations are recorded

Ready-to-Use Functions

Generates typed parameters, docstrings, and defaults - perfect for LLM agents

3. Generate Code

After recording, InverseUI will automatically generate code that you can use in your automation scripts. The generated code includes all the interactions you recorded, with parameters automatically detected for reusable inputs.

Download the generated Playwright code and integrate it into your existing automation framework, or use our Recording SDK to programmatically control the recording process.

Run with CLI

Run your recorded automations locally with automatic error recovery using the InverseUI CLI.

View on PyPI →

Install CLI

Requires Python 3.10+ and Google Chrome.

pip install inverseui

Login

Authenticate via browser, then paste the code into your terminal.

inverseui login

Run a Track

Execute a recorded track by its ID.

inverseui run <track_id>

Fix with AI

Automatically retry failing scripts with AI-generated fixes.

inverseui fix <track_id>

For the complete CLI reference including all options and advanced usage, see Developer Guides → CLI Reference.