# GeneSummary (genesummary.com) — read it, link to it, cite it.
#
# Pages are public and meant to be found through search engines. They are not a training
# set: collecting this site's content to train or fine-tune machine-learning models is
# not permitted (see /terms/). The crawlers below are the ones that collect for that
# purpose, or fetch pages for AI assistants; they are asked to stay out. Search indexing
# (Googlebot, Bingbot, DuckDuckBot, OAI-SearchBot, …) is allowed. OAI-SearchBot is
# deliberately not listed: it builds a search index that cites and links back, and its
# operator states it is not used for training.

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Claude-User
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

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

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: DuckAssistBot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

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

Sitemap: https://genesummary.com/sitemap.xml