Show HN: Huntsman – Self-hosted web scraper that turns pages into Markdown

Category: devtools

Tags: web-scraper, markdown, llm, self-hosted, go, firecrawl-compatible

Score: 7.0/10 (Innovation: 6, Technical: 7, Documentation: 8, Utility: 7)

Huntsman is a self-hosted web scraper that converts pages to clean Markdown for LLMs and search, using Lightpanda for JavaScript rendering and a Firecrawl-compatible API. It stands out for its efficiency, security defaults, and benchmarked performance against similar tools.

Target audience: backend developers, data engineers, AI/LLM engineers

Repository: https://github.com/TulipFarm/huntsman · Go · Apache-2.0 · 3 stars

View on Hacker News