# robots.txt for store.link
# Policy: allow search indexing AND AI training/input.
# Content Signals (https://contentsignals.org/) make this explicit so AI
# crawlers and downstream tools can honor the publisher's stated preference.

Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Default: open to all well-behaved crawlers.
User-agent: *
Allow: /

# Deliberately NOT disallowed here: /add-products-mockup and /loader-animation.
# Each serves
# <meta name="robots" content="noindex, nofollow"> from the page itself.
# A robots.txt Disallow would stop crawlers fetching the page at all, so they
# would never read that tag — and a URL with inbound links can stay indexed as
# a bare result. Crawling is allowed; indexing is refused at the page. They are
# also excluded from the sitemap.

# --- Search engines (explicit allow) ---

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# Apple: powers Siri, Spotlight and Safari suggestions
User-agent: Applebot
Allow: /

# --- AI / LLM crawlers (explicit allow) ---

# OpenAI: training crawler
User-agent: GPTBot
Allow: /

# OpenAI: search index crawler (powers ChatGPT browsing/search)
User-agent: OAI-SearchBot
Allow: /

# OpenAI: on-demand user-triggered fetches from ChatGPT
User-agent: ChatGPT-User
Allow: /

# Anthropic: training crawler
User-agent: ClaudeBot
Allow: /

# Anthropic: user-triggered fetches via Claude
User-agent: Claude-User
Allow: /

# Anthropic: search-style indexing
User-agent: Claude-SearchBot
Allow: /

# Anthropic (legacy)
User-agent: Claude-Web
Allow: /

# Anthropic (legacy)
User-agent: anthropic-ai
Allow: /

# Google: controls inclusion in Gemini / Vertex AI training/grounding
User-agent: Google-Extended
Allow: /

# Google: Vertex AI agent grounding fetches
User-agent: Google-CloudVertexBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Perplexity user-triggered
User-agent: Perplexity-User
Allow: /

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

# Meta / Llama
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Bytedance
User-agent: Bytespider
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

User-agent: cohere-training-data-crawler
Allow: /

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

# DuckDuckGo AI Assist
User-agent: DuckAssistBot
Allow: /

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

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

User-agent: Ai2Bot-Dolma
Allow: /

# Webz.io (feeds several training datasets)
User-agent: Omgilibot
Allow: /

User-agent: omgili
Allow: /

User-agent: Webzio-Extended
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# ImageSift
User-agent: ImagesiftBot
Allow: /

# Timpi
User-agent: TimpiBot
Allow: /

# Huawei
User-agent: PanguBot
Allow: /

# Semrush AI overview crawler
User-agent: SemrushBot-OCOB
Allow: /

# Structured summary for LLMs: https://store.link/llms.txt

Sitemap: https://store.link/sitemap.xml