Tech watch
← All linksExtracting structured content from web pages and browsing flows.
A compact CLI turns websites into commands tailored for AI agents, returning the useful information without loading tens of thousands of tokens. The repository documents its commands and supported sites, making it a practical way to reduce the cost of automated browsing.
only-cli
Scrapling is a Python scraping framework that adapts selectors when page structures change. It covers both a single request and larger crawling workflows.
Maxun records browser interactions to extract data, run automations, and monitor pages. Its repository describes an open-source solution that can be self-hosted.
changedetection.io monitors pages and reports changes such as price shifts or restocks. It can be self-hosted and sends alerts through multiple channels.
This repository groups data extraction APIs and tools by social platform. It provides a directory for comparing accessible data types and available integrations.
Firecrawl offers search, scraping and crawling with Markdown, JSON and screenshot outputs. Its API provides an extraction layer for workflows and agents using web content.
Firecrawl
This product listing introduces PhantomBuster’s data collection and lead generation automations. It provides an overview of use cases alongside launch history and user feedback.
Marina Baccaro
