# Allowlisted: search crawlers + user-initiated AI retrieval bots that cite sources.
User-agent: Googlebot
User-agent: Googlebot-News
User-agent: bingbot
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: YandexBot
User-agent: Twitterbot
User-agent: facebookexternalhit/1.1
User-agent: archive.org_bot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
Crawl-delay: 8
Disallow: /links/*/bookmark
Disallow: /links/*/upvote
Disallow: /links/*/downvote
Disallow: /links/*/comments
Disallow: /issues
Disallow: /topics/submit
Disallow: /links/submit
Disallow: /login
Disallow: /register
Disallow: /account
Disallow: /sessions
Disallow: /translations
Disallow: /pages
Disallow: /search

# Google Ads crawlers — full access.
User-agent: Mediapartners-Google
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
Allow: /

# AI training crawlers — explicit opt-out.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Amazonbot
User-agent: Diffbot
Disallow: /

Sitemap: https://s3.amazonaws.com/bala.static/sitemaps/index.xml.gz

User-agent: *
Disallow: /