# robots.txt for Cloudlabels Landing Page (cloudlabels.io)
# Last updated: 2026-02-04

# Allow all search engine crawlers
User-agent: *
Allow: /

# Allow Google specific bots
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Mobile
Allow: /

User-agent: Googlebot-News
Allow: /

# Allow Bing
User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: msnbot
Allow: /

# Allow Yahoo
User-agent: Slurp
Allow: /

# Allow DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Allow Baidu (for international reach)
User-agent: Baiduspider
Allow: /

# Allow Yandex (for international reach)
User-agent: Yandex
Allow: /

# Allow social media crawlers for rich link previews
User-agent: facebookexternalhit
Allow: /

User-agent: Facebot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Pinterest
Allow: /

User-agent: TelegramBot
Allow: /

# Allow SEO tools
User-agent: AhrefsBot
Allow: /
Crawl-delay: 5

User-agent: SemrushBot
Allow: /
Crawl-delay: 5

User-agent: MJ12bot
Allow: /
Crawl-delay: 5

# AI answer engines / generative search (GEO)
# Explicitly welcome the crawlers that power AI Overviews, ChatGPT,
# Perplexity, and Claude so Cloudlabels content can be cited as a source.
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

# CCBot (Common Crawl) - used to train many models; allowed for visibility.
User-agent: CCBot
Allow: /

# Block aggressive/malicious bots
User-agent: AhrefsBotXXX
Disallow: /

User-agent: MJ12botXXX
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# Disallow internal/development paths
User-agent: *
Disallow: /api/
Disallow: /*.json$
Disallow: /out/

# Sitemap location
Sitemap: https://www.cloudlabels.io/sitemap.xml

# LLM-friendly content map (for AI answer engines)
# https://www.cloudlabels.io/llms.txt