PageSift — self-hosted web scraper and document parser for LLMs ✓ Verified
Also known as: pagesift
Added to TheBestApplications on Oct 31, 2026
Productivity · PC · Web
No reviews yet — be the first to try it.
⭐ 175 GitHub Stars (popularity on GitHub — not a user rating)
About this app
PageSift is a high-performance, self-hosted web scraper and document converter designed specifically for AI agents and LLMs. It fetches URLs with optional JavaScript rendering or parses local files including PDFs, Word, Excel, and PowerPoint documents, outputting clean Markdown and structured metadata. It offers multiple interfaces including a Firecrawl-compatible HTTP API, a Jina Reader endpoint, an MCP server, CLI, and SDKs for Python and Node.js. Built in Rust for low memory usage and high speed, it handles single pages, batch crawling, and site maps while respecting robots.txt and rate limits.
Reviews
Sign in with Google to leave a review.
No reviews yet.