Web Scraping
Crawling sites and extracting content. As of 2026-11-21, 922 indexed products match this subcategory (190 with full profiles); 633 were published in the last 90 days, against 147 in the 90 days before, faster than the catalogue as a whole. By GitHub stars, Firecrawl leads, holding 24% of the stars of the 744 products here with their own repository. The most common form is MCP servers (96% of indexed products).
SubcategorySegment label: Crowded, outpacing the catalogue DER
Segment statistics
Whole catalogue (all 922 indexed products, not only profiled ones). Calculated 2026-11-21.
Crowded, outpacing the catalogue. Among the largest fifth of nodes at its level, and its launches grew faster than the catalogue’s over the last two 90-day windows. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.112, attention is spread as if across about 9 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 886 | 96.1% | 156 |
| Agent skills | 13 | 1.4% | 13 |
| Plugins | 8 | 0.87% | 8 |
| Agent projects | 5 | 0.54% | 5 |
| Rules packs | 2 | 0.22% | 1 |
| Libraries | 2 | 0.22% | 2 |
| Infrastructure | 2 | 0.22% | 2 |
| AI APIs | 2 | 0.22% | 2 |
| Agent SDKs | 1 | 0.11% | 1 |
| Frameworks | 1 | 0.11% | 0 |
4 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Web CrawlingCrawling whole sites and sitemaps. | 231 | 56 | 160 | Crowded, outpacing the catalogue |
| Structured ScrapingPulling structured records from pages. | 159 | 18 | 139 | Outpacing the catalogue |
| Content ExtractionTurning a URL into clean text or Markdown. | 85 | 27 | 37 | Established |
| Proxies & Anti-botProxies and stealth for scraping at scale. | 60 | 21 | 25 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (190 of 922), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | FirecrawlAPI that crawls and scrapes websites into clean Markdown or structured JSON, with search, map and agentic extract endpoints. | API | firecrawl | 206k | today | AGPL-3.0 | ||
| 2 | Browser UsePython library that lets LLM agents control a Playwright/CDP browser by reading page state and issuing actions, with a hosted cloud option. | Library | browser-use | 122k | today | MIT | ||
| 3 | Scrapling MCP ServerWeb scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported. | MCP server | D4Vinci | 105k | 4d ago | BSD-3-Clause | ||
| 4 | Crawl4AIOpen-source async web crawler that outputs LLM-ready Markdown and structured extraction, running headless browsers locally. | Library | unclecode | 88k | 1d ago | Apache-2.0 | ||
| 5 | ai-website-cloner-templateClone any website with one command using AI coding agents | Agent project | JCodesMore | 40k | 11d ago | MIT | ||
| 6 | changedetection.io (official)Official changedetection.io MCP: web page change tracking, back-in-stock and price alerts. | MCP server | changedetection.io | 36k | 1d ago | Apache-2.0 | ||
| 7 | CloakBrowserStealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed. | Agent project | CloakHQ | 33k | 1d ago | MIT | ||
| 8 | StagehandBrowser automation SDK that mixes Playwright-style code with natural-language act, extract and observe primitives and an agent mode. | SDK | browserbase | 26k | today | MIT | ||
| 9 | moliBest headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust | Agent project | lexmount | 24k | today | Apache-2.0 | ||
| 10 | Douyin_TikTok_Download_API🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API,支持 AI agent 通过 MCP 调用与离线语音转文字,Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up. | MCP server | Evil0ctal | 22k | today | Apache-2.0 | ||
| 11 | Skill_SeekersConvert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection | MCP server | yusufkaraaslan | 15k | 5d ago | MIT | ||
| 12 | nanobrowserOpen-source AI agent for web automation. Use your real, logged-in browser to automate daily tasks. | Agent project | nanobrowser | 14k | 4d ago | Apache-2.0 | ||
| 13 | SeleniumBase MCPStealthy browser automation, testing, and web-scraping via CDP Mode. | MCP server | seleniumbase | 13k | today | MIT | ||
| 14 | Jina ReaderAPI that converts any URL into LLM-friendly Markdown (r.jina.ai) and runs web search returning cleaned page content (s.jina.ai). | API | jina-ai | 12k | 6mo ago | Apache-2.0 | ||
| 15 | nopecha-extensionAutomated CAPTCHA solver for your browser. Works with Selenium, Puppeteer, Playwright, and more. | Agent project | NopeCHALLC | 11k | 1mo ago | MIT | ||
| 16 | google-maps-scraperscrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place | Agent skill | gosom | 8.3k | today | MIT | ||
| 17 | Firecrawl MCP ServerFirecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search. | MCP server | firecrawl | 7.9k | 1d ago | MIT | ||
| 18 | skillsBrowser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing. | Agent skill | browser-act | 6.4k | 17d ago | MIT | ||
| 19 | wigoloLocal-first web intelligence MCP server for AI coding agents | MCP server | KnockOutEZ | 5.6k | 1d ago | — | ||
| 20 | exaExa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers, and more. | Plugin | exa-labs | 5.3k | today | MIT | ||
| 21 | designlangMeasure any site's design system, score how generic a page looks, check UI against your brand. | MCP server | Manavarya09 | 5.2k | 3d ago | MIT | ||
| 22 | stealth-browser-mcpStealth browser automation for AI agents over MCP and the Chrome DevTools Protocol: navigation, network hooks, DOM extraction, and pixel-accurate UI cloning. | MCP server | vibheksoni | 3.4k | 1d ago | MIT | ||
| 23 | brightdata-mcpBright Data's Web MCP server enabling AI agents to search, extract & navigate the web | MCP server | brightdata | 2.7k | 3d ago | MIT | ||
| 24 | google-maps-scraper-kitFree, open-source Google Maps scraper for lead generation (Python, no API key, no Docker). Exports name, phone, email, website, rating and Instagram/Facebook/LinkedIn/TikTok/YouTube/X links to CSV. 100 places with emails in 44 s; --grid beats Google's 120 cap. MX email check, ad-pixel detection. Skill for Claude Code, Codex and Cursor. | Agent skill | Mahanaicoach | 2.6k | 2d ago | AGPL-3.0 | ||
| 25 | webclawWeb scraping, search, crawling, structured extraction and research for AI agents. | MCP server | 0xMassi | 2.4k | today | AGPL-3.0 | ||
| 26 | anysearch-mcp-serverUnified real-time search MCP server supporting general web search, vertical domain search, parallel batch search, and full-page URL content extraction. | MCP server | anysearch-ai | 2.1k | 5d ago | Apache-2.0 | ||
| 27 | boss-zhipin-scraperBoss直聘爬虫 / BOSS直聘职位数据抓取工具,基于 Chrome CDP 协议复用真实登录态,绕过字体反爬,输出明文薪资 JSON/CSV + 薪资技能分析。A Chrome-CDP-based BOSS Zhipin job scraper/crawler. | Agent skill | eatmoreduck | 1.8k | 18d ago | MIT | ||
| 28 | awesome-claude-pluginsAutomated index of Claude Code plugins and adoption metrics across GitHub repositories, powered by a Node.js/TypeScript crawler | Plugin | quemsah | 1.7k | today | — | ||
| 29 | openserpSelf-hosted web search for AI agents and SEO. Google, Bing, Yandex, Baidu, DuckDuckGo & Ecosia, rendered in a real browser: ranked results and clean page Markdown. API, CLI, MCP 🎉 | MCP server | karust | 1.6k | 1d ago | MIT | ||
| 30 | CRW Web ScraperOpen-source web scraper for AI agents with scrape, crawl, and map tools | MCP server | fastcrw | 1.3k | today | AGPL-3.0 | ||
| 31 | CRW Web ScraperOpen-source web scraper for AI agents with scrape, crawl, and map tools | MCP server | us | 1.3k | today | AGPL-3.0 | ||
| 32 | fastCRWScrape, crawl, map & search the web. Open-source, self-hostable Rust crawler & search for AI agents. | MCP server | us | 1.3k | today | AGPL-3.0 | ||
| 33 | anymdAny file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP. | MCP server | SylphxAI | 1.1k | today | MIT | ||
| 34 | CitraCitra — PDF answers with page-level proof: structure, tables, OCR, and page citations. | MCP server | SylphxAI | 1.1k | today | MIT | ||
| 35 | PDF Reader MCPEvidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence. | MCP server | SylphxAI | 1.1k | today | MIT | ||
| 36 | seo-opsSEO foundation checks as an Agent Skill: give it a URL, get a crawler's-eye pass/fail report with evidence. 26 structural checks, zero LLM, deterministic. | Agent skill | tigerless-labs | 992 | 15d ago | — | ||
| 37 | x-readerUniversal content reader MCP Server for 10+ platforms | MCP server | runesleo | 992 | 10d ago | MIT | ||
| 38 | huashu-md-htmlmd/html 双向流水线 · 三个能力一站式:万物→md / md→精美html / html→md。封装 markitdown + Pandoc + html-to-markdown + trafilatura。4 套反 AI slop 主题。Claude Code skill. | Agent skill | alchaincyf | 948 | 6d ago | MIT | ||
| 39 | chatgpt-seoTurn a page, draft, or SEO export into a sourced fix plan inside ChatGPT. | Agent skill | AgriciDaniel | 938 | 1mo ago | MIT | ||
| 40 | chatWebChatWeb can crawl web pages, read PDF, DOCX, TXT, and extract the main content, then answer your questions based on the content, or summarize the key points. | Infrastructure | SkywalkerDarren | 916 | 6mo ago | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| YouTube | 31 | 3.4% |
| 14 | 1.5% | |
| Playwright | 14 | 1.5% |
| 11 | 1.2% | |
| Google Maps | 10 | 1.1% |
| GitHub | 9 | 1.0% |
| Google Ads | 6 | 0.7% |
| Shopify | 6 | 0.7% |
| Workday | 5 | 0.5% |
| Docker | 4 | 0.4% |
| Solana | 4 | 0.4% |
| Google Cloud | 3 | 0.3% |
| X (Twitter) | 3 | 0.3% |
| Google Analytics | 2 | 0.2% |
| Kubernetes | 2 | 0.2% |
Launches per month
New Web Scraping products per monthSRC
Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-12 | 2 |
| 2025-03 | 3 |
| 2025-04 | 2 |
| 2025-08 | 1 |
| 2025-09 | 6 |
| 2025-10 | 8 |
| 2025-11 | 3 |
| 2025-12 | 8 |
| 2026-01 | 3 |
| 2026-02 | 17 |
| 2026-03 | 25 |
| 2026-04 | 28 |
| 2026-05 | 19 |
| 2026-06 | 44 |
| 2026-07 | 66 |
| 2026-08 | 63 |
| 2026-09 | 142 |
| 2026-10 | 270 |
| 2026-11 | 192 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
| Opportunity | Competition | Confidence | Score |
|---|---|---|---|
| Coverage gap: Proxies & Anti-botProxies & Anti-bot | High | Low | 56.1 |
| Coverage gap: Content ExtractionContent Extraction | High | Low | 53.9 |
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .