Vision-model web extraction tools

LLM Scraper

TypeScript library that turns webpages into structured data via LLMs

Diffbot

Computer vision and ML API that extracts structured web data

Jina Reader

Turns any URL into clean markdown via a simple API prefix

JigsawStack

Small AI models via API for web scraping, search, and OCR

Skyvern

Open source browser automation agent using LLMs and vision

Bytebot

Open-source AI agent that automates tasks via a virtual desktop

WebVoyager

Open-source multimodal web agent with a 643-task benchmark

GAIA

Benchmark for evaluating general AI agents on reasoning and tool use

VisualWebArena

Benchmark of 910 visually grounded tasks for multimodal web agents