FetchFox

Open-source AI scraper with a hosted API and dashboard

By Nathan KesslerUpdated Jul 27, 2026

Each tool is evaluated against our methodology using public docs, vendor demos, and hands-on testing.

Some links on this page are affiliate links. We earn a commission if you sign up – at no additional cost to you. Our editorial assessment is independent and never paid. How we review.

What is FetchFox?

FetchFox is an AI-powered web scraping and data-extraction tool. It ships as an open-source npm library (MIT license) and as a hosted scraping API with a dashboard. Plain-English instructions get processed by LLMs to pull the data, defaulting to OpenAI's gpt-4o-mini with support for Google Gemini and OpenRouter models, while Playwright handles browser automation and JavaScript rendering. It also covers multi-step and multi-page crawls, streaming or callback result handling, structured JSON output, and proxy selection, plus a Chrome extension, an MCP server, and n8n integration nodes.

Our verdict

The open-source library and hosted API give teams a choice between self-hosting and a managed dashboard, and LLM-driven plain-English extraction cuts setup effort for straightforward crawls. There is no disclosed funding or customer base in the public record, and at 158 GitHub stars it has a smaller track record than more established API-first alternatives.

Categories:

AI Extraction

AI extraction tools sit between a raw page and your database: you describe the fields you want, and a model returns structured JSON or LLM-ready markdown without hand-written selectors. They hold up well when page layouts change often, at the cost of per-request model spend and the occasional wrong field.