BrowserGPT enables users to control web browsers using natural language commands, powered by GPT-4 and Playwright. It's designed for users who want to automate browser interactions through intuitive, conversational prompts, offering a powerful way to navigate and manipulate web content without writing explicit code.

How It Works

The project leverages OpenAI's GPT-4 to interpret natural language instructions and generate corresponding Playwright code snippets. Playwright then executes these code snippets to perform actions within a browser instance. This approach allows for dynamic and flexible browser automation, where the AI translates user intent into executable browser commands.

Quick Start & Requirements

• Install dependencies: npm install
• Set up OpenAI API key: Create a .env file with OPENAI_API_KEY=your_openai_api_key.
• Install Playwright executables: npx playwright install
• Run: npm run start
• Requires Node.js and an OpenAI API key.

Highlighted Details

• Natural language control of browser actions.
• Integrates GPT-4 with Playwright for code generation and execution.
• Supports various models, including gpt-4-1106-preview for its large token context.
• Command-line options for model selection, output path, viewport size, and starting URL.

Maintenance & Community

The project is maintained by mayt. No specific community channels or roadmap details are provided in the README.

Licensing & Compatibility

Licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The script is a demonstration and may not perform flawlessly on all tasks or websites. Generated code might fail execution, and the model may misinterpret inputs, requiring users to provide more detailed prompts or rephrase requests.