# 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: /

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

# houdiniswap.com robots.txt
# Brand, content, SEO, blog — Webflow

# Default: allow all general crawlers
User-Agent: *
Allow: /
Disallow: /cdn-cgi/

# =====================================================
# AI crawlers — explicitly allowed for LLM discoverability
# Each agent must be declared separately. Wildcards do not
# apply to AI bots — they only honour their exact name.
# =====================================================

# OpenAI — training data crawler
User-Agent: GPTBot
Allow: /

# OpenAI — ChatGPT Search / live retrieval (separate from GPTBot)
User-Agent: OAI-SearchBot
Allow: /

# OpenAI — ChatGPT on-demand fetch (when a user clicks a link)
User-Agent: ChatGPT-User
Allow: /

# Anthropic — Claude training crawler
User-Agent: ClaudeBot
Allow: /

# Anthropic — Claude on-demand fetch
User-Agent: Claude-Web
Allow: /

# Anthropic — Claude search index (newer)
User-Agent: anthropic-ai
Allow: /

# Google — opt-in toggle for Gemini, AI Overviews, and Vertex AI
User-Agent: Google-Extended
Allow: /

# Google — search index (default crawler, included for clarity)
User-Agent: Googlebot
Allow: /

# Perplexity — search and answer engine
User-Agent: PerplexityBot
Allow: /

# Perplexity — on-demand fetch when user clicks a link
User-Agent: Perplexity-User
Allow: /

# Microsoft — Bing index + Copilot grounding
User-Agent: Bingbot
Allow: /

# Microsoft — explicit Copilot/Bing Chat agent
User-Agent: BingPreview
Allow: /

# Amazon — Alexa / Rufus / shopping AI
User-Agent: Amazonbot
Allow: /

# Apple — Apple Intelligence training opt-in
User-Agent: Applebot
Allow: /

User-Agent: Applebot-Extended
Allow: /

# Meta — Meta AI grounding agent
User-Agent: meta-externalagent
Allow: /

# Meta — Llama training
User-Agent: FacebookBot
Allow: /

# Cohere — RAG / enterprise LLM training
User-Agent: cohere-ai
Allow: /

# Cohere — on-demand fetch
User-Agent: cohere-training-data-crawler
Allow: /

# Mistral
User-Agent: MistralAI-User
Allow: /

# ByteDance / TikTok / Doubao — large APAC search/AI surface
User-Agent: Bytespider
Allow: /

# Diffbot — knowledge graph (powers many enterprise AI products)
User-Agent: Diffbot
Allow: /

# DuckDuckGo
User-Agent: DuckDuckBot
Allow: /

# Common Crawl — public crawl, used as training corpus by most labs
User-Agent: CCBot
Allow: /

# Brave Search index
User-Agent: Bravebot
Allow: /

# You.com search and AI
User-Agent: YouBot
Allow: /

# Phind — developer-focused AI search
User-Agent: PhindBot
Allow: /

# Kagi Search
User-Agent: KagiBot
Allow: /

# Yandex — large non-Western index
User-Agent: YandexBot
Allow: /



Sitemap: https://houdiniswap.com/sitemap.xml