Hydrafetch

Hydrafetch is a web data API for LLMs and agents.

От сообществаРаботаетБез входаГлобальныйБесплатноМожет изменять данные

Что умеет

  • Scrape: Turn a URL into clean, LLM-ready markdown and structured data.
  • Map: Enumerate a site's URLs from its sitemap and links, without scraping them.
  • Search: Search the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra credit per page.

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Hydrafetch is a web data API for LLMs and agents. Send a URL and get back clean Markdown, the page's own structured data, schema-shaped JSON, links, or a summary, with the navigation, banners and boilerplate stripped out.

Scrape one page, map a whole site, run a search, or extract to a schema, all through one API with one response shape. It also resolves a company's brand from its domain — logos, real colours, fonts — and can render a page to a screenshot or read a site's design system.

Every fetch costs one credit a page whatever it took to retrieve, and failed requests are never billed.

Список инструментов сервера (9)

Технические названия из tools/list. Нужны только разработчикам.

scrapeTurn a URL into clean, LLM-ready markdown and structured data.
mapEnumerate a site's URLs from its sitemap and links, without scraping them.
searchSearch the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra credit per page.
brandA company's brand from its domain: logos for light and dark backgrounds, its real colours, name, description and socials. Answers 'what is this company' far better than a raw page dump.
logoA company's logo as a directly embeddable image URL, chosen for the background you name. Use this rather than brand when the mark is all you need — it costs a fifth as much and returns one asset instead of the whole record.
extractPull typed structured data from one or more URLs by JSON schema or prompt.
styleguideA site's design system read from computed styles in a real browser: colours by role with contrast ratios, the type scale, corner radius and button styling. Values defined through CSS variables come back resolved to the hex actually painted.
screenshotRender a page in a real browser and capture a PNG, returning its public URL. Use when the question is what the page looks like rather than what it says.
imagesHarvest a page's images with their metadata, without rendering it. Cheaper than a screenshot and returns the source images rather than a picture of the page.