# LINKENCE robots.txt
# We allow general search engines and most LLM answer engines.
# Training-only crawlers we don't want are explicitly disallowed below.

# --- Search engines ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

# --- Social previews ---
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# --- Answer engines that surface real-time results in chat UIs ---
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Applebot
Allow: /

# --- Training-grounding crawlers (allowed for now; flip to Disallow to opt out) ---
User-agent: GPTBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

# --- Crawlers we explicitly do not want ---
User-agent: Bytespider
Disallow: /

# --- Default ---
User-agent: *
Allow: /

Sitemap: https://linkence.ai/sitemap.xml

# Expanded marketing digest (emitted by `npm run build:seo` to dist/llms-full.txt on production):
# https://linkence.ai/llms-full.txt