Converts web pages and HTML strings into clean, LLM-optimized Markdown with metadata extraction and token estimation. It uses a lightweight, browserless approach to provide token-efficient output for more effective LLM processing.
Transforms already-rendered HTML into LLM-friendly Markdown with metadata, using Mozilla Readability, Turndown, and DOMPurify. No outbound requests; ideal for post-JavaScript content extraction.
Converts messy HTML into clean semantic markdown with integer IDs, enabling LLMs to navigate and interact with web pages efficiently using intent-guided filtering and diff-based updates.
Converts HTML webpages to clean Markdown format, reducing size by ~90-95% while preserving tables, images, and important content. Supports both simple HTTP fetch and Playwright browser mode for JavaScript-heavy or authenticated pages.
