# robots.txt — Keepp (keepp.link)
# We welcome every crawler, including AI and LLM bots, across the whole site
# (this file governs keepp.link and the /blog section — robots.txt is read only
# at the domain root). The wildcard already allows everyone; the named AI agents
# are listed explicitly so our intent to permit AI search and AI training is
# unambiguous.

User-agent: *
Allow: /

# --- AI / LLM crawlers, explicitly welcomed ---

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

# Google (Gemini / Vertex AI training)
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Microsoft / Bing (Copilot)
User-agent: bingbot
Allow: /

# Common Crawl (feeds many LLMs)
User-agent: CCBot
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# ByteDance / TikTok
User-agent: Bytespider
Allow: /

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

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

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

# Others
User-agent: PetalBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: Timpibot
Allow: /

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