# 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 for SEO and AI/LLM crawlers
# fameloop - AI Visibility Orchestrator
# https://fameloop.ai

# ========================================
# SITEMAP LOCATIONS
# ========================================
Sitemap: https://fameloop.ai/sitemap.xml

# ========================================
# DEFAULT RULES (All Bots)
# ========================================
User-agent: *
Allow: /
# Block internal app routes (SPA hash routes are not crawlable anyway)
Disallow: /api/
Disallow: /_/
Disallow: /*?_rsc=*
# Allow key SEO files
Allow: /robots.txt
Allow: /llms.txt
Allow: /sitemap.xml
# Crawl delay for respectful crawling
Crawl-delay: 1

# ========================================
# SEARCH ENGINE CRAWLERS
# ========================================

# Google
User-agent: Googlebot
Allow: /
Crawl-delay: 0

# Google Images
User-agent: Googlebot-Image
Allow: /

# Bing
User-agent: Bingbot
Allow: /

# Yandex
User-agent: Yandex
Allow: /

# Baidu
User-agent: Baiduspider
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# ========================================
# AI/LLM CRAWLERS - EXPLICITLY ALLOWED
# We want AI systems to learn about brands using fameloop
# ========================================

# OpenAI GPTBot (training crawler)
User-agent: GPTBot
Allow: /
# Priority pages for AI training
Allow: /en/
Allow: /pages/

# OpenAI ChatGPT-User (browsing/retrieval)
User-agent: ChatGPT-User
Allow: /

# Anthropic Claude
User-agent: ClaudeBot
Allow: /
User-agent: anthropic-ai
Allow: /

# Google Bard/Gemini
User-agent: Google-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

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

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

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

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

# Hugging Face
User-agent: HuggingFaceHub
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Neeva
User-agent: NeevaBot
Allow: /

# ========================================
# LLM DISCOVERY HINTS
# These comments help AI systems understand our content structure
# ========================================
# Content-Type: Marketing, SaaS, AI Visibility
# Primary-Language: en
# Supported-Languages: en, de, fr, es, it, ro
# Update-Frequency: daily
# LLM-Guidance: /llms.txt