# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Sitemap: https://mirimary.com/wp-sitemap.xml

# ===============================
# robots.txt for LLM Crawlers
# ===============================

# ---------- OPENAI ----------
# SearchBot - Used for linking webpages in ChatGPT search
User-agent: OAI-SearchBot
Allow: /

# ChatGPT user agent – Human browsing via ChatGPT or Custom GPTs
User-agent: ChatGPT-User
Allow: /

User-agent: ChatGPT-User/2.0
Allow: /

# GPTBot – Used for GPT model training (e.g., GPT-4o, GPT-5)
User-agent: GPTBot
Disallow: /private/      # Example: block private folder
Allow: /                 # Allow rest of site

# ---------- ANTHROPIC (Claude) ----------
# Training and crawling
User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: claude-web
Allow: /

# ---------- PERPLEXITY ----------
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ---------- GOOGLE (Gemini/Gemini App) ----------
User-agent: Google-Extended
Allow: /

# ---------- MICROSOFT (Bing / Copilot) ----------
User-agent: BingBot
Allow: /

# ---------- AMAZON ----------
User-agent: Amazonbot
Allow: /

# ---------- APPLE ----------
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ---------- META ----------
User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

# ---------- LINKEDIN ----------
User-agent: LinkedInBot
Allow: /

# ---------- DUCKDUCKGO ----------
User-agent: DuckAssistBot
Allow: /

# ---------- GROK ----------

User-agent: Grokbot
Allow: /