{"full_name":"unclecode/crawl4ai","owner":"unclecode","name":"crawl4ai","shard":"1","url":"https://github.com/unclecode/crawl4ai","description":"Official 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.","homepage":"https://crawl4ai.com/?ref=github-about","topics":["ai","ai-agents","crawler","data-extraction","llm","markdown","mcp","open-source","playwright","python","rag","scraper","web-crawler","web-crawling","web-scraping"],"tag_pages":["ai","ai-agents","crawler","data-extraction","llm","markdown","mcp","open-source","playwright","python","rag","scraper","web-crawler","web-scraping"],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/12494079?u=413d68156031fdfe74861491b75ffe6d426d8228&v=4","created_at":"2024-05-09T09:48:50Z","pushed_at":"2026-11-13T13:32:17Z","metrics":{"stars":87397,"forks":9117,"watchers":422,"issues":1085,"prs":975,"releases":23,"issues_open":65,"issues_closed":1020,"prs_open":286,"prs_closed":389,"prs_merged":300,"discussions":442},"growth":{"day":{"stars":44,"forks":2,"base_day":"2026-11-15"},"week":{"stars":269,"forks":36,"base_day":"2026-11-09"},"month":{"stars":2016,"forks":252,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[80186,80786,81112,81199,81286,81551,81902,81976,82046,82106,82177,82523,83473,83562,83684,83747,83826,83869,84032,84080,84154,84211,84259,84304,84413,84477,84609,84644,84690,84786,84844,84897,85009,85082,85146,85381,85451,85534,85617,85663,85715,85850,85920,85986,86039,86116,86177,86316,86403,86462,86534,86602,86778,86842,87128,87170,87220,87267,87277,87314,87353,87397],"forks":[8303,8351,8369,8374,8379,8414,8446,8450,8453,8461,8466,8512,8622,8634,8647,8660,8667,8674,8691,8687,8697,8703,8715,8718,8730,8737,8754,8758,8764,8780,8788,8799,8820,8823,8835,8865,8874,8879,8893,8900,8908,8926,8938,8941,8943,8948,8962,8977,8988,9000,9008,9013,9043,9051,9081,9084,9090,9100,9102,9107,9115,9117],"watchers":[408,413,413,413,414,414,415,415,415,413,413,413,415,414,414,415,415,415,416,417,418,418,418,418,419,419,419,419,420,422,423,423,423,423,423,424,425,425,424,425,425,425,426,425,425,425,419,419,418,419,418,418,418,419,423,423,423,423,423,423,422,422],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,59,61,62,65,65,65],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,272,279,279,281,281,286]},"boards":{"total":193},"same_owner":[],"issues":[{"number":731,"title":"[Bug]: When extracting data with scroll_full_page, only the final elements get parsed","comments":22,"created_at":"2025-02-20T22:31:27Z"},{"number":1256,"title":"[Bug]: Memory Leak on Repeated /md Requests via Docker (MacOS) — Container Crashes Randomly Over Time","comments":15,"created_at":"2025-06-29T01:48:19Z"},{"number":2251,"title":"[docs] DOM XSS: unescaped innerHTML interpolation in docs/apps/linkdin graph view template (5 sinks)","comments":5,"created_at":"2026-09-12T01:52:43Z"},{"number":2098,"title":"unclecode-litellm shadows the upstream litellm package; the quarantine that motivated the fork has been lifted","comments":4,"created_at":"2026-07-25T09:34:36Z"},{"number":2380,"title":"[Bug]: After a streamed deep crawl is stopped early, the next deep crawl returns only the start page","comments":3,"created_at":"2026-10-15T14:51:47Z"},{"number":2202,"title":"[Bug]: Browser pages and renderer processes accumulate for weeks on non-streaming /crawl (Docker 0.9.2)","comments":3,"created_at":"2026-08-26T17:55:47Z"},{"number":2058,"title":"Config option to disable is_blocked() post-crawl content veto","comments":3,"created_at":"2026-07-08T08:30:08Z"},{"number":2023,"title":"Feature request: opt-out for the mandatory token when binding non-loopback (Kubernetes / trusted-network deployments)","comments":2,"created_at":"2026-06-19T22:08:18Z"}],"discussions":[{"number":2556,"title":"Exploring Moli with Crawl4AI","comments":0,"category":"General","created_at":"2026-11-13T07:51:58Z"},{"number":2549,"title":"Chopper: a small open model that cuts only the needed sentences out of retrieved text","comments":0,"category":"Show and tell","created_at":"2026-11-12T19:47:01Z"},{"number":2508,"title":"RAG Source Receipts: offline content and processing fingerprints for Crawl4AI outputs (early MVP)","comments":0,"category":"Show and tell","created_at":"2026-11-06T11:04:16Z"},{"number":2492,"title":"[Feature Request]: Staged build to decrease image size","comments":0,"category":"Feature requests","created_at":"2026-11-03T22:44:27Z"},{"number":2488,"title":"Docker image update for HTTP2Shell (CVE-2026-111497)","comments":1,"category":"Forums - Q&A","created_at":"2026-11-03T02:41:25Z"},{"number":2465,"title":"Proposal: versioned content blocks and meaningful change events","comments":0,"category":"Feature requests","created_at":"2026-10-29T15:18:02Z"},{"number":2446,"title":"Show and tell: Hardening Downstream Database Tools Against Indirect Prompt Injections in Crawl4AI Pipelines","comments":0,"category":"Show and tell","created_at":"2026-10-26T07:23:58Z"},{"number":2430,"title":"Crawl4AI is #2 in Data and scraping for AI on Archestack (badge, if you want it)","comments":0,"category":"Show and tell","created_at":"2026-10-21T15:31:13Z"}],"latest_release":{"name":"Release v0.9.5","tag":"v0.9.5","published_at":"2026-10-14T10:25:39Z","body":"## 🎉 Crawl4AI v0.9.5 Released!\n\n### 📦 Installation\n\n**PyPI:**\n```bash\npip install crawl4ai==0.9.5\n```\n\n**Docker:**\n```bash\ndocker pull unclecode/crawl4ai:0.9.5\ndocker pull unclecode/crawl4ai:latest\n```\n\n**Note:** Docker images are being built and will be available shortly.\nCheck the [Docker Release workflow](https://github.com/unclecode/crawl4ai/actions/workflows/docker-release.yml) for build status.\n\n### 📝 What's Changed\nSee [CHANGELOG.md](https://github.com/unclecode/crawl4ai/blob/main/CHANGELOG.md) for details.\n","is_prerelease":false},"readme":true,"readme_zh":false,"news":[{"title":"Crawl4AI is an open-source, LLM-friendly web crawler and scraper","url":"https://github.com/unclecode/crawl4ai","hn":"https://news.ycombinator.com/item?id=43827993","source":"Hacker News","lang":"en","date":"2025-04-29","points":7,"comments":2},{"title":"Crawl4AI: Open-Source Web Crawler for Seamless AI Data Scraping","url":"https://github.com/unclecode/crawl4ai","hn":"https://news.ycombinator.com/item?id=41689534","source":"Hacker News","lang":"en","date":"2024-09-29","points":6,"comments":0},{"title":"crawl4ai: The Adaptive Intelligence Update","url":"https://github.com/unclecode/crawl4ai/releases/tag/v0.7.0","hn":"https://news.ycombinator.com/item?id=44543172","source":"Hacker News","lang":"en","date":"2025-07-12","points":4,"comments":0},{"title":"Ask HN: What do you use (AI based) web crawlers for?","url":"https://news.ycombinator.com/item?id=46733548","hn":"https://news.ycombinator.com/item?id=46733548","source":"Hacker News","lang":"en","date":"2026-01-23","points":3,"comments":0},{"title":"Crawl4AI","url":"https://github.com/unclecode/crawl4ai","hn":"https://news.ycombinator.com/item?id=41747108","source":"Hacker News","lang":"en","date":"2024-10-05","points":2,"comments":0},{"title":"Crawl4AI: Open-source web crawler and scraper for LLMs","url":"https://github.com/unclecode/crawl4ai","hn":"https://news.ycombinator.com/item?id=48857017","source":"Hacker News","lang":"en","date":"2026-07-10","points":1,"comments":0},{"title":"Crawl4AI: Open-Source LLM Friendly Web Crawler and Scraper","url":"https://github.com/unclecode/crawl4ai","hn":"https://news.ycombinator.com/item?id=45963180","source":"Hacker News","lang":"en","date":"2025-11-18","points":1,"comments":0},{"title":"Crawl4ai – open-source web crawler for your AI agent","url":"https://github.com/unclecode/crawl4ai","hn":"https://news.ycombinator.com/item?id=43048990","source":"Hacker News","lang":"en","date":"2025-02-14","points":1,"comments":0},{"title":"Crawl4AI：開源網頁爬蟲工具，專為 LLM 數據提取而設計","url":"https://www.techritual.com/2026/07/13/526843/","source":"techritual","lang":"zh","date":"2026-07-12"},{"title":"crawl4ai 从零到上手：GitHub 排名第一的开源 AI 爬虫，5 行代码抓取任意网页","url":"https://blog.csdn.net/Aliaoo/article/details/161612655","source":"blog.csdn","lang":"zh","date":"2026-06-02"},{"title":"A Coding Implementation of Crawl4AI for Web Crawling, Markdown Generation, JavaScript Execution, and LLM-Based Structured Extraction","url":"https://www.marktechpost.com/2026/04/14/a-coding-implementation-of-crawl4ai-for-web-crawling-markdown-generation-javascript-execution-and-llm-based-structured-extraction/","source":"marktechpost","lang":"en","date":"2026-04-13"},{"title":"【GitHub开源AI精选】Crawl4AI：LLM专属极速开源爬虫利器、1秒处理百万级数据","url":"https://blog.csdn.net/xiaobing259/article/details/147874552","source":"blog.csdn","lang":"zh","date":"2025-05-12"},{"title":"A Coding Guide to Asynchronous Web Data Extraction Using Crawl4AI: An Open-Source Web Crawling and Scraping Toolkit Designed for LLM Workflows","url":"https://www.marktechpost.com/2025/04/23/a-coding-guide-to-asynchronous-web-data-extraction-using-crawl4ai-an-open-source-web-crawling-and-scraping-toolkit-designed-for-llm-workflows/","source":"marktechpost","lang":"en","date":"2025-04-22"},{"title":"Crawl4AI：为大语言模型打造的开源网页数据采集工具","url":"https://news.qq.com/rain/a/20250417A02NQF00","source":"腾讯网","lang":"zh","date":"2025-04-17"},{"title":"️ Crawl4AI로 웹 크롤링을 초고속 자동화해 보세요!","url":"https://note.com/life_to_ai/n/nd44732147fb3?hl=ko","source":"note","lang":"en","date":"2024-08-15"},{"title":"8 GitHub Repos That Automate Your Work With AI Agents (All Free) ← I recommend this one","url":"https://news.google.com/rss/articles/CBMiXEFVX3lxTE5hTXQtcUJYcGphT1BZMzd1WEZZTFVzWDRKTHFCRmU3WE5Cc0UwSVJYdFVJOG0xOS13c19BZG5WaHJCZ2x1MlBSRnI5ajBNX252ZHk5cE8zeGduR0pp?oc=5","source":"YouTube","lang":"en","date":"2026-11-06"},{"title":"10 GitHub Repos for Scraping the Internet in 2026 (Real Stars)","url":"https://news.google.com/rss/articles/CBMiiAFBVV95cUxPMWZEd05SYXh2UUhNa2I4S2JBZjRfVktYUnhTV1FBdW5JMFgxRGVqWXdybGUxUkZyQTZGTGpYTlZNdXhoWTF3Ymd5T1dnTWJORExBdjJNTXpoQmQ3UnNQaVREMVRHMnZZWjdtTDZFcVllb3hISjVuVkN0VGY4NUV0RE50cWdDR0NR?oc=5","source":"Pasquale Pillitteri","lang":"en","date":"2026-06-30"},{"title":"2026 年抓取互联网的 10 个 GitHub 仓库 (附真实星标)","url":"https://news.google.com/rss/articles/CBMihAFBVV95cUxORGZEaDBndmMzUDdFYUdOTnRmeG9QQUw0RHRIZUFCTlNTMncyTjJIUWRWOVpLejNMa011VU5XeXNaZzQ1R0dEWk1IMWQweUFNZ2hyQjJMdlE3cy0xSDYxYTB0QllyOFh0QU1nNWxXVjRTazVzdDd1MTJ5R2VnbXdVRFpVenA?oc=5","source":"Pasquale Pillitteri","lang":"zh","date":"2026-06-30"},{"title":"litellm: Credential Stealer Hidden in PyPI Wheel","url":"https://news.google.com/rss/articles/CBMihwFBVV95cUxOY0tHV0NBYmIyQTRZV05wNDdBd1ZkOU9CSjk4QkU4TXptdGF6ZzNnRjZ5cTRNMlhfOUZrQUNmbFZYMUpudXoxVV9wVFlvLWMwMFEyem5HWG1zS3pyN2xqUUotSUJSRTgxTUt0WUtxODdhd0NuZU5QaUdNemNkemdTWXk0aXU2R3M?oc=5","source":"Step Security","lang":"en","date":"2026-03-24"},{"title":"OpenAI Atlas等AI浏览器暴露Web Agent安全风险！南洋理工破解底层机制","url":"https://news.google.com/rss/articles/CBMiSEFVX3lxTE1YOVNwVGdNRUJwU1VqaTV6NDRUOFFpeWxWb3BNMVhDdnJtOHNuQVM4ejhNS2hEaFpUM1JZdWtpcnlQaElwRXR6Sg?oc=5","source":"智源社区","lang":"zh","date":"2025-11-06"},{"title":"Top 7 AI Web Scraping Tools","url":"https://news.google.com/rss/articles/CBMiY0FVX3lxTE13Vlp3Sm0yWGRCMm82V3RsY1laTlFqbHRWNGJEMEQwMWQxRDItTjVxNGlfdXBGcnZmREs5UDI1ay1kb1FRaVU3enAyZVV4YmJETXJVYXhncy13aGUxVXZhNEZkSQ?oc=5","source":"KDnuggets","lang":"en","date":"2025-09-08"},{"title":"Crawl4AI：开源 LLM 友好型 Web 爬虫和抓取工具","url":"https://news.google.com/rss/articles/CBMiP0FVX3lxTE0wb0NhNF9fRlN3SmVYSnJVLTZodlEtTXhLSVIyekkwNGJVcUlMazVQOVVJNU1tNHlzcTliQ2VoNA?oc=5","source":"blog.upx8.com","lang":"zh","date":"2024-10-05"}],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}