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.
Repository Index
60,121 visible repositories in the index
1–6 of 6 · Most stars
Python scraper based on AI
- scraping
- scraping-python
- llm
- web-crawler
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
- web-scraping
- text-extraction
- nlp
- html2text
Translated✨WeChat Official Account assistant that fits reading habits, WeChat Official Account to MarkDown, WeChat Official Account to PDF, scheduled updates of subscribed Official Account articles, generate RSS feeds for WeChat Official Accounts, export WeChat Official Account subscription feeds, supports Webhook/API/AI Agent integration for WeChat Official Accounts, subscribe to WeChat Official Accounts, WeChat Official Account assistant, WeChat Official Account reading, WeChat Official Account interface, WeChat Official Account crawler, WeChat Official Account monitoring, tag-based subscription to WeChat Official Accounts, WeChat Official Account source, WeChat Official Account book reading, WeChat Official Account articles, WeChat Official Account framework, WeChat Official Account management, WeChat Official Account source, WeChat Official Account platform, WeChat Official Account code, WeChat Official Account system, WeChat Official Account source code
- rss-feed
- rss-hub
- weichat
- weixin
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.
Translated📚 WeChat Reading (微信读书) lossless full-book export tool — one-click export of dual-font, finely typeset PDF / EPUB / plain Markdown notes (compatible with Obsidian & Notion), solving the problem of missing characters when turning pages on the web version.