# https://www.robotstxt.org/robotstxt.html
# Jarmin welcomes search engines and AI assistants.
#
# Content signals (contentsignals.org) state how this content may be used,
# separately from who may crawl it:
#   search   = yes  index it and link to it
#   ai-input = yes  use it to answer a question now, with attribution
#   ai-train = no   do not train or fine-tune models on it
# We want to be found and cited. We do not want to be absorbed.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Crawlers are listed by what they do, because the distinction decides whether
# we are eligible to be cited in an AI answer.
# See /llms.txt for a concise, agent-friendly description of Jarmin.

# --- Retrieval and search: these are the ones that get us cited. ---

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- Training: allowed, subject to the ai-train signal above. ---

User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: CCBot
Allow: /

Sitemap: https://jarmin.ai/sitemap.xml