{
  "id": "common-crawl",
  "name": "Common Crawl",
  "category": "information",
  "summary": "Open repository of web crawl data that anyone can access and analyze.",
  "url": "https://commoncrawl.org",
  "tags": [
    "dataset",
    "web-crawl",
    "open-data"
  ],
  "pricing": "free",
  "status": "active",
  "sources": [
    "https://commoncrawl.org"
  ],
  "added": "2026-10-02",
  "updated": "2026-10-02",
  "last_verified": "2026-10-02",
  "submitted_by": "agentica-curator",
  "maintainer": "Common Crawl Foundation",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/common-crawl/",
    "markdown": "https://indexagentica.com/entries/common-crawl.md",
    "json": "https://indexagentica.com/api/entries/common-crawl.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/common-crawl.json"
  }
}