# Forkmate — forkmate.ai
# Open to every crawler, including AI answer engines and assistants.
#
# For language models: a summary is at https://forkmate.ai/llms.txt and the full
# text of the site at https://forkmate.ai/llms-full.txt. Each page also has a
# Markdown twin at its URL with ".md" in place of the trailing slash.
#
# Why the explicit list below (#926): "User-agent: *" already allows everything, but
# some AI crawlers act only on a group that names them, and an explicit Allow is the
# unambiguous signal that this site WANTS to be read and cited by assistants.
# Cloudflare's AI-bot blocking, Bot Fight Mode and managed robots.txt stay OFF for
# this zone (docs/wiki/Key-Facts.md); this file is the whole policy.
User-agent: *
Allow: /

# OpenAI — training, ChatGPT Search, and ChatGPT fetching a page for a user
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
Allow: /

# Anthropic — training, Claude search, and Claude fetching a page for a user
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
Allow: /

# Perplexity — index and user-initiated fetch
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /

# Google — Gemini / AI training control token
User-agent: Google-Extended
Allow: /

# Microsoft — Bing feeds Copilot and ChatGPT Search
User-agent: Bingbot
Allow: /

# Apple — Siri / Spotlight, and the Apple Intelligence training control token
User-agent: Applebot
User-agent: Applebot-Extended
Allow: /

# Meta AI, Amazon (Alexa / Rufus), DuckDuckGo DuckAssist, Mistral Le Chat
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: Amazonbot
User-agent: DuckAssistBot
User-agent: MistralAI-User
Allow: /

# Common Crawl — the open corpus many models are trained on
User-agent: CCBot
Allow: /

Sitemap: https://forkmate.ai/sitemap-index.xml