Hub / Инструменты

Инструменты

60 записей, по убыванию рейтинга. Как считается рейтинг.

• browser-use/browser-useOpen-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.рейтинг 88.6 · 120 362 звёзд · MIT · сообщество
• D4Vinci/Scrapling🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_devрейтинг 88.2 · 99 960 звёзд · BSD-3-Clause · сообщество
• unclecode/crawl4aiOfficial Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.рейтинг 87.8 · 87 112 звёзд · Apache-2.0 · сообщество
• docling-project/doclingGet your documents ready for gen AIрейтинг 87.3 · 70 308 звёзд · MIT · сообщество
• scrapy/scrapyScrapy, a fast high-level web crawling & scraping framework for Python.рейтинг 87.1 · 65 284 звёзд · BSD-3-Clause · сообщество
• PaddlePaddle/PaddleOCRTurn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.рейтинг 85.8 · 92 452 звёзд · Apache-2.0 · сообщество
• JCodesMore/ai-website-cloner-templateClone any website with one command using AI coding agentsрейтинг 85.8 · 38 871 звёзд · MIT · сообщество
• dgtlmoon/changedetection.ioBest and simplest tool for website change detection, web page monitoring, and website change alerts. Perfect for tracking content changes, price drops, restock alerts, and website defacement monitoring— MCP included! all for free or enjoy our SaaS plan!рейтинг 85.6 · 35 658 звёзд · Apache-2.0 · сообщество
• CloakHQ/CloakBrowserStealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed.рейтинг 85.3 · 32 784 звёзд · MIT · сообщество
• opendataloader-project/opendataloader-pdfPDF Parser for AI-ready data. Automate PDF accessibility. Open-source.рейтинг 85.1 · 30 247 звёзд · Apache-2.0 · сообщество
• ScrapeGraphAI/Scrapegraph-aiPython scraper based on AIрейтинг 85 · 32 635 звёзд · MIT · сообщество
• apify/crawleeCrawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.рейтинг 84.8 · 26 384 звёзд · Apache-2.0 · сообщество
• browserbase/stagehandThe SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.рейтинг 84.8 · 25 985 звёзд · MIT · сообщество
• lexmount/moliBest headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rustрейтинг 84.5 · 23 068 звёзд · Apache-2.0 · сообщество
• Evil0ctal/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.рейтинг 84.2 · 21 290 звёзд · Apache-2.0 · сообщество
• MODSetter/SurfSenseAir-gapped, privacy-focused, open-source NotebookLM alternative. AI agent that researches, transforms, and edits your documents. Join our Discord: https://discord.gg/ejRNvftDp9рейтинг 83.6 · 16 808 звёзд · Apache-2.0 · сообщество
• Unstructured-IO/unstructuredConvert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.рейтинг 83.5 · 15 700 звёзд · Apache-2.0 · сообщество
• nanobrowser/nanobrowserOpen-source AI agent for web automation. Use your real, logged-in browser to automate daily tasks.рейтинг 83.2 · 14 264 звёзд · Apache-2.0 · сообщество
• seleniumbase/SeleniumBasePython APIs for web automation, testing, and bypassing bot-detection.рейтинг 83 · 13 233 звёзд · MIT · сообщество
• jo-inc/camofox-browserStealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.рейтинг 82.8 · 12 209 звёзд · MIT · сообщество
• jhy/jsoupjsoup: the Java HTML parser, built for HTML editing, cleaning, scraping, and XSS safety.рейтинг 82.7 · 11 413 звёзд · MIT · сообщество
• yusufkaraaslan/Skill_SeekersConvert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detectionрейтинг 82.6 · 15 295 звёзд · MIT · сообщество
• pinchtab/pinchtabHigh-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.рейтинг 82.5 · 10 564 звёзд · MIT · сообщество
• apify/crawlee-pythonCrawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Parsel, BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.рейтинг 82.2 · 9 655 звёзд · Apache-2.0 · сообщество
• NopeCHALLC/nopecha-extensionAutomated CAPTCHA solver for your browser. Works with Selenium, Puppeteer, Playwright, and more.рейтинг 81.9 · 11 098 звёзд · MIT · сообщество
• mherrmann/heliumLighter web automation with Pythonрейтинг 81.9 · 8 321 звёзд · MIT · сообщество
• firecrawl/firecrawl-mcp-serverOfficial Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.рейтинг 81.7 · 7 783 звёзд · MIT · сообщество
• gosom/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 placeрейтинг 81.7 · 7 641 звёзд · MIT · сообщество
• mindee/doctrdocTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.рейтинг 81.2 · 6 424 звёзд · Apache-2.0 · сообщество
• run-llama/llama_cloud_servicesKnowledge Agents and Management in the Cloudрейтинг 80.2 · 4 272 звёзд · MIT · сообщество