# dabyte.ai — AI crawlers are explicitly allowed. This site exists to be read and cited
# by answer engines; the dataset is published under CC BY 4.0. See /humans.txt for who runs it.

# --- AI answer engines: allow full crawl (this is the whole point of the network) ---
User-agent: GPTBot
Allow: /

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: Google-Extended
Allow: /

User-agent: Bingbot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Applebot-Extended
Allow: /

# --- everyone else: allowed, nothing hidden ---
User-agent: *
Allow: /

# Content Signals (contentsignals.org). Allow/Disallow says whether you may FETCH;
# this says what you may DO with what you fetched. We say yes to all three on
# purpose: the dataset is CC BY 4.0 and the entire point of publishing it is to be
# read, quoted and trained on. Saying no here would contradict our own licence.
Content-Signal: ai-train=yes, search=yes, ai-input=yes

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