Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.

Use LLMs to robustly extract web data

Fully automated and hands-free, accurately extracting and understanding web content — powered by machine learning agents.

Low-Cost Cross-Domain Web Structured Information Extraction using specialized LoRA adapters.

Replayable Browser Agent

基于Scala Akka的分布式主题网络爬虫

Automatic extraction of the information on local event from a webpage with Machine Learning

A powerful and lightweight web scraping library with LLM extraction capabilities. This library combines web scraping with AI-powered content extraction using either OpenAI or OpenRouter APIs.

Predicting product recommendation score using the data available on the website of the client

Free local web search/extraction router for AI agents. Go CLI + MCP, BYOK/free-first routing, keyless DDGS/Scrapling fallback, setup writers and client guides.

Self-hosted web scraping and Markdown extraction for AI agents

Programming assignments for Web Information Extraction and Retrieval, FRI UL, 2021. PA1: standalone webcrawler of .gov.si web sites, PA2: approaches of the structured web data extraction, PA3: Data processing and indexing and Data retrieval.

Get google URL results from search query

MarkGrab plugin for Claude Code — web content extraction to LLM-ready markdown

Structured web-extraction tool plugin with schema, provenance, and drift awareness.

This project is a command-line tool that extracts text from web pages and PDF files, including scanned documents. It supports various extraction methods. This tool is ideal for data scraping, NLP preprocessing, and content analysis.

pinterest data extraction toolkit

Giving Agent Eyes to see and interact with internet. Agent Eye is an MCP server that wraps Playwright and exposes browser tools for local AI agents

Local-first search tool layer for AI agents, built with FastAPI, SearXNG, and Trafilatura.

Extracting links from any website.