Browser4

Browser4 is a browser automation engine for developers building AI agents, web research tools, and data collection workflows. It controls real Chrome browsers and handles interactive pages that require clicks, forms, or JavaScript before their data is accessible.

• Autonomous browser tasks: Agents accept natural-language requests, plan actions across pages, and collect results for tasks such as product research and comparison.
• Structured extraction: Combine LLM extraction with CSS selectors, X-SQL queries, and machine learning to turn page content into structured data; selector queries and ML extraction don't consume LLM tokens.
• Repeatable workflows: Automate forms, uploads, and downloads, capture screenshots or PDFs, and save browser session state for later work.
• Parallel crawling: Process batches of URLs across multiple browser contexts, with retries and recovery for long-running collection jobs.
• Reusable page knowledge: An experience store retains learned selectors, interaction hints, and known blockers for subsequent tasks.

Browser4 is open source under Apache 2.0 and can run on your own machine or server. Its CLI supports Windows, macOS, and Linux, while MCP connects browser controls to AI agents. Extraction can work with live pages or stored HTML snapshots. The token-free extraction path uses selectors and machine learning; autonomous reasoning and LLM extraction use language models.