Skip to content

Introduction to Diffbot

Diffbot builds AI models that read and transform the unstructured web into knowledge.

Unlike flat data dumps from traditional web scraping, facts structured by Diffbot are linked to each other like nodes in a graph. "Diffbot" mentioned in this MIT Technology Review article is resolved to the same "Diffbot" on LinkedIn or diffbot.com.

This graph structure is key to enabling intelligent AI applications like the Knowledge Graph and GraphRAG, but most people simply know us for Extract API, the automatic web scraper that doesn't use any rules.

Diffbot is used by companies all over the world to tap into unstructured data from the public web at immense scale.

Building with Diffbot

Diffbot APIs make it possible to:

Diffbot APIs can also be combined to power highly intelligent automated systems, such as this automated sanctions tracker.

We'd love to hear about the intelligent apps you're building with Diffbot. Find us on LinkedIn, Bluesky, and Mastodon.

Where do I start?

A good place to start is adding diffbot-skills to your agent harness of choice and prompt it for a tour.

prompt
Give me a tour of Diffbot skills

Prefer to roll up your sleeves? This site contains our entire API Reference. Head on over to Authentication to set up your token, then pick one of our APIs to start structuring the web.

Should you run into any blockers you can't find an answer to in these docs, reach out to support.

Returning to Diffbot

Welcome back! If you've used us in the past, you already know how things work around here. Chances are, the API you're thinking of is still 100% supported (we've been maintaining our APIs for over 15 years!).

Check out what's new in the Changelog, or jump right back in.