# Thessly. Independent research on senior living and aging care.
#
# Policy: Thessly is built to be cited, not ingested. Answer engines that
# fetch a page in order to attribute it are welcome. Crawlers whose purpose
# is to absorb the dataset into model weights are not.
#
# Attribution guidance: https://thessly.org/press

User-agent: *
Allow: /
Disallow: /search
Disallow: /*?

# --- Classic search: fully allowed ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# --- Answer engines: allowed, because they cite ---
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot
Allow: /

# --- Model-training crawlers: not permitted ---
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: imgproxy
Disallow: /

# --- SEO-tool crawlers: not permitted ---
# They do nothing for search visibility, they ignore Crawl-delay, and each
# request spends the free request allowance that real search and answer
# engines need. Also refused at the firewall, so this is a courtesy notice.
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: AwarioBot
Disallow: /

Sitemap: https://thessly.org/sitemap-index.xml