firecrawl
Web Scraping
v2.11.0
Firecrawl is a web data platform built for AI agents that need to find, read, and act on live web content.3mo agoAGPL-3.0DockerDemoAdvanced
Projects tagged #Web Scraping
~/index>
--sort
42 projects· by score
Projects
Crawl4AI
Web Scraping
v0.9.5Crawl4AI is an open-source web crawler and scraper designed for LLMs and AI agents.14d agoApache-2.0DockerDemoModerate
gpt-researcher
AI Chat
v3.7.0GPT Researcher is an autonomous deep-research agent that turns a single question into a detailed, cited report of 2,000+ words.1mo agoApache-2.0DockerModerate
Lightpanda
Browser Automation
1.0.2Lightpanda is a headless browser written from scratch in Zig for people who crawl, scrape or test pages whose content depends on JavaScript, and for AI agent…5d agoAGPL-3.0DockerEasy
changedetection.io
Monitoring & observability
0.60.10changedetection.io monitors websites for content changes and notifies users when updates are detected.2d agoApache-2.0DockerModerate
FreshRSS
Feed Reader
1.30.4FreshRSS is an aggregator for RSS and Atom feeds that you run on your own hardware and open from any recent browser.6d agoAGPL-3.0DockerDemoEasy
CloakBrowser
Browser Automation
chromium-v155.0.8059.39.2-proCloakBrowser is a stealth Chromium browser built at the C++ source level, designed to evade bot detection systems during web automation.todayMITDockerModerate
Obscura
Web Scraping
v0.2.5Obscura is a browser engine built in Rust without any UI, aimed at automation software rather than at people browsing pages: it executes real JavaScript thro…7d agoApache-2.0DockerEasy
skyvern
Automation
v1.0.56Skyvern automates browser-based work — logging into portals, filling forms, extracting data and downloading files — by letting vision LLM agents navigate sit…14d agoAGPL-3.0DockerModerate
camofox-browser
Browser Automation
v1.18.1camofox-browser is a Node.js server that puts a stealth browser behind a REST API for AI agents and scrapers.21d agoMITNo DockerEasy
maxun
Web Scraping
v0.1.0Maxun is an open-source platform for pulling structured data out of websites, aimed at developers and at non-technical teams alike.3d agoAGPL-3.0DockerModerate
RSS-Bridge
RSS
2025-08-05This PHP application builds syndication feeds for sites which no longer publish them, covering news outlets, social networks, marketplaces, package repositor…27d agoUnlicenseDockerModerate
flaresolverr
Proxy
v3.5.2FlareSolverr is a proxy server whose job is getting past bot-protection walls, mainly Cloudflare's but also DDoS-Guard's.1mo agoMITDockerEasy
browserless
Web Scraping
v2.57.3Browserless lets you deploy headless browsers in Docker containers, either running on your own infrastructure or using their cloud service.5d agoDockerEasy
surfsense
RAG
v2.2.5SurfSense is a desktop AI research notebook for people handling files they cannot upload to a cloud service.1d agoApache-2.0No DockerEasy
steel
Browser Automation
v0.5.4-betaSteel Browser is an open-source browser automation platform designed for AI agents and web automation tasks.2mo agoApache-2.0DockerModerate
webclaw
Web Scraping
v0.7.0webclaw is a Rust-based web content extraction toolkit designed for AI agents and retrieval pipelines.8d agoAGPL-3.0DockerDemoModerate
KindleEar
Feed Reader
3.3KindleEar is a Python web application for self-hosting a personal news-to-ebook pipeline: it collects RSS/ATOM/JSON feeds and Calibre recipe websites on a da…6mo agoMITDockerDemoModerate
Fredy
Web Scraping
30.1.1Fredy monitors 29 property portals across Germany, Austria, Switzerland, Spain, Italy, Portugal and France.1d agoApache-2.0DockerDemoEasy
binhex-official-byparr
Web Scraping
v3.0.4Byparr is a self-hosted HTTP service that drives a real, stealthed headless browser so it can pass anti-bot challenges on its own and hand back usable cookies.2mo agoGPL-3.0DockerEasy
crw
Web Scraping
v0.39.0fastCRW is a web scraping and search API designed for AI agents, offering a Firecrawl-compatible REST API with endpoints for scraping single URLs, crawling e…todayAGPL-3.0DockerDemoModerate
OpenSERP
API
v0.8.15This free, MIT-licensed project lets you run a local REST service that fetches live search results from six major engines and returns them in a consistent JS…todayMITDockerDemoModerate
TRAWL
Web Scraping
v1.9.3TRAWL is a self-hosted web scraping engine designed for applications and AI agents.todayAGPL-3.0DockerModerate
Kibitzr
Monitoring & observability
v8.0.1Kibitzr is a personal web assistant that monitors web pages for changes and sends notifications when something happens.1y agoMITDockerModerate
Multiscrape
Home Automation
v9.1.0ha-multiscrape is a **Home Assistant custom component** that extends the built-in `scrape` and `rest` sensors by enabling users to scrape **multiple values f…1mo agoMITNo DockerModerate
anakin
Web Scraping
v0.1.1AnakinScraper OSS is an open-source, Go-based web scraping API aimed at AI agents and RAG pipelines: it converts any URL into clean markdown, HTML, or struct…4mo agoAGPL-3.0No DockerEasy
PriceBuddy
v1.0.57PriceBuddy is a self-hostable web app for watching product prices at whatever online retailers you shop at, aimed at people whose favourite store has no offi…todayGPL-3.0DockerEasy
pullmd
Document Conversion
v3.16.0PullMD is a self-hosted tool that transforms web pages, documents, images, audio files, and YouTube videos into clean Markdown.todayAGPL-3.0DockerEasy
