# Folio Defence: independent research. Index it, search it, quote it with credit and a link to the page.
# Never use it to train, fine-tune or evaluate AI / machine-learning models.
# Terms of use: https://www.foliodefence.com/terms/#ai · TDM rights reserved: https://www.foliodefence.com/.well-known/tdmrep.json
# robots.txt is a request, not a lock: these lines say what is permitted.

# Search engines: welcome.
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: YandexBot
User-agent: Slurp
User-agent: Baiduspider
User-agent: SeznamBot
User-agent: MojeekBot
User-agent: Qwantbot
User-agent: Yeti
User-agent: PetalBot
Allow: /

# AI search and user-requested fetchers that answer with a link to the source: allowed for search and
# citation only; their operators state these agents do not train models.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
Allow: /

# AI training and dataset crawlers: not permitted, anywhere on this site.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: Google-CloudVertexBot
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: img2dataset
User-agent: LAIONDownloader
User-agent: laion-huggingface-processor
User-agent: omgili
User-agent: omgilibot
User-agent: Webzio-Extended
User-agent: Diffbot
User-agent: FriendlyCrawler
User-agent: Timpibot
User-agent: Crawlspace
User-agent: VelenPublicWebCrawler
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: bedrockbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: MistralAI-Training
User-agent: xAI-Grok
User-agent: GrokBot
User-agent: Bytespider
User-agent: TikTokSpider
User-agent: DoubaoBot
User-agent: DeepSeekBot
User-agent: QwenBot
User-agent: ERNIEBot
User-agent: Hunyuan
User-agent: MoonshotBot
User-agent: KimiBot
User-agent: PanguBot
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: YiBot
User-agent: ChatGLM-Spider
User-agent: ICC-Crawler
User-agent: Cotoyogi
User-agent: SBIntuitionsBot
User-agent: Factset_spyderbot
User-agent: ISSCyberRiskCrawler
User-agent: ImagesiftBot
User-agent: aiHitBot
User-agent: Panscient
User-agent: EchoboxBot
User-agent: ElevenlabsCrawler
User-agent: Scrapy
User-agent: imageSpider
User-agent: newsai
User-agent: MyCentralAIScraperBot
User-agent: NagetBot
Disallow: /

# Everyone else: index and search welcome; training is not (Content Signals, contentsignals.org).
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

Sitemap: https://www.foliodefence.com/sitemap.xml