Auto WebCursor is a Chrome extension that automates web browsing tasks using AI. It allows users to control the cursor and perform actions on web pages through simple text or voice inputs. By interacting with the HTML elements, WebCursor can automatically navigate pages, and perform actions like click or input with simple text prompts.
- LLM-based Computer Use: Control your and automate web tasks using text or voice commands, allowing the LLM to click, read, and input.
- Accessibility First: Designed to make web navigation easier for individuals with disabilities.
- Voice and Text Input: Interact with the web using natural language.
- Customizable Workflows: Create personalized workflows for common tasks.
- Clone this repository to your local machine:
git clone https://github.com/Richard28277/auto-webcursor.git
- Navigate to the project folder:
cd auto-webcursor
- Download the ZIP file from the GitHub repository:
- Go to the repository page.
- Click the Code button and select Download ZIP.
- Extract the ZIP file to a folder on your computer.
- Open Google Chrome and go to
chrome://extensions/. - Enable Developer Mode by toggling the switch in the top-right corner.
- Click Load unpacked.
- Select the folder where you cloned the repository or extracted the ZIP file (e.g.,
auto-webcursor). - The extension will now appear in your list of installed extensions.
-
Open the Extension:
- Click the Auto WebCursor icon in the Chrome toolbar to open the side panel.
-
Enter Commands:
- Type or speak your command in the input field (e.g., "Click the login button").
- The AI will process your command and perform the action on the web page.
-
Customize API:
- Use the settings menu to modify the API provider and model type.
This project is licensed under the MIT License. See the LICENSE file for details.