Huntsman
github.com/tulipfarm/huntsman- Category
- Developer Tools
- Rank
- No. 1879Tools index
- Pricing
- Open Source
- Type
- TOOL
- GitHub
- 3 stars
- Latest release
- v0.2.1
- Date
About
Huntsman is a self-hosted web scraper that converts web pages into clean Markdown for LLMs and search. It renders JavaScript with Lightpanda, removes ads, trackers and cookie banners, and exposes a Firecrawl-compatible scrape API from a single Go binary and container. It also supports batch and whole-site crawls with a SQLite-backed queue, so existing Firecrawl clients may only need a new base URL.
Tags
web-scrapingmarkdownself-hostedllmgofirecrawl
Tech Stack
GoDocker
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.