AI-Ready Website Change Feed - Chunked Diffs for RAG Pipelines

LinkedIn Jobs Scraper (Public Guest Search, No Login)

mibedk/linkedin-jobs-public-search

Scrapes LinkedIn job postings (title, company, location, description, posted date, apply link) from LinkedIn's public guest job-search pages. No login, no cookies, no account-ban risk — only data LinkedIn already serves to logged-out visitors.

Website Changes Detector

tri_angle/website-changes-detector

Automatically track website changes (new, updated, or removed pages) using periodic re-crawling. Supports flexible crawling settings, a list of URLs or sections of websites, antiblocking, filtering by keywords, and more.

Web-to-Markdown Generator for AI & RAG Pipelines

profitstack/web-to-markdown-generator-for-ai-rag-pipelines

Convert any website into clean, heading-based chunking, LLM-ready Markdown for RAG and AI agents.

Website Change Notification API

gr_59017/website-change-notification-api

Monitors websites for content changes using Cheerio. Compares current and previous page versions and notifies when changes are detected. Ideal for tracking notices, updates, pricing changes, and announcements.

Website Content Crawler

worshipful_knife/website-content-crawler

Deep crawl websites and extract clean text, Markdown, or HTML for LLMs, RAG, and AI apps. Removes navigation, ads, cookie banners. Supports headless browser & HTTP. Sitemap discovery, URL scoping, file downloads. Feed ChatGPT, LangChain, LlamaIndex, Pinecone. The cheapest content crawler on Apify.

Crawl any website and extract clean Markdown and plain text optimized for AI ingestion, RAG pipelines, and LLM context. Readability-style main content extraction removes ads, navs, and footers. Configurable depth, concurrency, and page limits. Pay-per-page.

MCP Website RAG Ingestion Tool

glowing_glove/mcp-website-rag-ingestion-tool

MCP-ready tool for AI agents to crawl public webpages, clean text, and return source-linked chunks for RAG and knowledge-base workflows.

Website to Markdown [💰$1.5/1K] | Clean HTML for AI & RAG

ahmed_jasarevic/website-to-clean-markdown-ai-rag-ready

Convert any website into clean, noise-free Markdown for LLM training, RAG pipelines and Custom GPTs. Strip HTML junk, keep the content, and cut OpenAI token costs. From $2.80 per 1K results.

Website to RAG Dataset

sebastian-actors/website-to-rag-dataset

Convert public websites, docs, blogs, and XML sitemaps into clean Markdown, structured metadata, and stable chunks for RAG pipelines and vector databases.

Sitemap Change Detector

tri_angle/sitemap-change-detector

Identify and monitor sitemaps for specified websites. Retrieve only the new, updated, or removed URLs since the last crawl.