# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content


User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# Avatarooms - robots.txt
# https://avatarooms.com
# Use only standard directives: User-agent, Allow, Disallow, Sitemap (no Content-Signal etc.)

# === Standard search engine crawlers ===
User-agent: *
Allow: /
Disallow: /assets/images/bg-*
Disallow: /assets/images/card-bg-*
Disallow: /uk/welcome.html
Disallow: /welcome1.html
Disallow: /welcome2.html
Disallow: /welcome-h2.html
Disallow: /welcome-home.html
Disallow: /landing-v1.html
Disallow: /en/landing-v1.html

# === LLM / AI crawlers - explicitly allowed ===
# OpenAI (ChatGPT, SearchGPT)
User-agent: GPTBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.md

User-agent: ChatGPT-User
Allow: /
Allow: /llms.txt
Allow: /llms-full.md

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.md

User-agent: Claude-Web
Allow: /

# Google (Gemini / AI Overviews)
User-agent: Google-Extended
Allow: /

# Microsoft (Copilot / Bing AI)
User-agent: Bingbot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

# Apple (Applebot for Siri / Apple Intelligence)
User-agent: Applebot
Allow: /

# Common Crawl (used by many AI training sets)
User-agent: CCBot
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# Sitemap
Sitemap: https://avatarooms.com/sitemap.xml