{"name":"crawl4ai","repo":"unclecode/crawl4ai","url":"https://midorreal.com/project/unclecode-crawl4ai","repository":"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.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/unclecode/crawl4ai","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/unclecode/crawl4ai","checked":"22 Nov 2026"},"homepage":{"value":"https://crawl4ai.com/?ref=github-about","source":"https://crawl4ai.com/?ref=github-about","checked":"22 Nov 2026"},"last_release":{"value":"v0.9.6, 20 Nov 2026","source":"https://github.com/unclecode/crawl4ai/releases","checked":"22 Nov 2026"},"releases":{"value":"24","source":"https://github.com/unclecode/crawl4ai/releases","checked":"20 Nov 2026"},"contributors":{"value":"114","source":"https://github.com/unclecode/crawl4ai/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/unclecode/crawl4ai","checked":"22 Nov 2026"}},"stars":87648.0,"writeup":{"what_it_is":"Crawl4AI is an open-source web crawler and scraper that turns web pages into Markdown for LLMs and AI agents. It can be run as a Python library, a Docker server, or used through a hosted cloud API.","audience":"Developers building LLM, RAG, AI agent, or data pipeline applications","claims":[{"kind":"broad","claim":"Produces clean, LLM-ready Markdown from web pages","excerpt":"turns any website into clean, LLM-ready Markdown for RAG, AI agents and data pipelines","status":"too_broad"},{"kind":"specific","claim":"Free tier includes 1,000 credits every month for the cloud service","excerpt":"Free: 1,000 credits every month, 10 a minute, 2 at a time","status":"not_checked"},{"kind":"specific","claim":"Discovers URLs with prefetch mode that the README says is faster","excerpt":"`prefetch=True` finds URLs 5 to 10 times faster","status":"not_checked"},{"kind":"specific","claim":"Can crawl up to 10,000 URLs in a background job via the cloud","excerpt":"up to 50 URLs in one streamed call, or 10,000 in a background job","status":"not_checked"},{"kind":"specific","claim":"Supports Chromium, Firefox and WebKit browsers","excerpt":"**Chromium, Firefox and WebKit**","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-30"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":81,"reality":84,"gap":-3,"momentum":0.7,"confidence":85,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T07:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-20T09:46:52+00:00","text":"Latest release v0.9.6","source":"https://github.com/unclecode/crawl4ai/releases"},{"date":"2025-03-04T14:21:20+00:00","text":"First release","source":"https://github.com/unclecode/crawl4ai/releases"},{"date":"2024-05-09T09:48:50+00:00","text":"Repository created","source":"https://github.com/unclecode/crawl4ai"}],"cite":"crawl4ai is a GitHub project at https://github.com/unclecode/crawl4ai written mainly in Python, described there as \"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\".","attribution":"Data from Mid or Real, https://midorreal.com/project/unclecode-crawl4ai, checked 22 November 2026. Attribution with a link is required.","still_real":null}