# 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.

# 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
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# robots.txt — LLMO Best Practices
# Last updated: 2026-03-04
# Purpose: Allow all AI crawlers for maximum AI visibility (LLMO)
# Learn more: https://ai-fy.me

# DEFAULT: Allow all standard web crawlers
User-agent: *
Allow: /

# OPENAI — ChatGPT / GPT-4 browsing / SearchGPT
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /

# GOOGLE — Gemini / AI Overviews / Search Generative Experience
User-agent: Googlebot
Allow: /
User-agent: Google-Extended
Allow: /

# ANTHROPIC — Claude
User-agent: anthropic-ai
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
# PERPLEXITY — Perplexity AI
User-agent: PerplexityBot
Allow: /

# META — Meta AI / Llama
User-agent: FacebookBot
Allow: /
User-agent: Meta-ExternalAgent
Allow: /
User-agent: Meta-ExternalFetcher
Allow: /

# MICROSOFT — Copilot / Bing AI
User-agent: Bingbot
Allow: /
User-agent: msnbot
Allow: /

# APPLE — Apple Intelligence / Siri
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

# AMAZON — Alexa / Amazon AI
User-agent: Amazonbot
Allow: /

# COHERE — Command / RAG platforms
User-agent: cohere-ai
Allow: /

# YOU.COM — You AI
User-agent: YouBot
Allow: /

# BYTEDANCE — Doubao / TikTok AI
User-agent: Bytespider
Allow: /

# AI2 — Allen Institute for AI (research / academic)
User-agent: AI2Bot
Allow: /

# DIFFBOT — Knowledge graph / structured AI data
User-agent: Diffbot
Allow: /

# TIMPI — Decentralised AI search index
User-agent: Timpibot
Allow: /

# IASK — iAsk AI search
User-agent: iaskspider
Allow: /
# 
# SITEMAPS — Help AI crawlers discover all content
# 
Sitemap: https://ai-fy.me/sitemap.xml