AutoBrowse is a developer library enabling LLM-driven web automation. By leveraging large language models, it plans and executes browser actions—searching, navigating, interacting, and extracting information from web pages. Using a planner-executor pattern, it breaks down high-level tasks into step-by-step actions, handling JavaScript rendering, form inputs, link traversal, and content parsing. It outputs structured data or summaries, making it ideal for research, data collection, automated testing, and competitive intelligence workflows.

browse-for-me leverages headless Chromium via Puppeteer controlled by OpenAI models to interpret user-defined instructions. Users create configuration files specifying target URLs, actions like clicking, form submission, and data points for extraction. The agent executes each step autonomously, handles errors with retries, and returns structured JSON or plain-text summaries. With support for multi-step sequences, scheduling, and environment variables, it streamlines tasks like web scraping, site monitoring, automated testing, and content summarization.