# informuje.me — vítáme vyhledávače a odpovídací asistenty, odmítáme trénování modelů.
# We welcome search engines and live-retrieval answer engines. We refuse bulk AI training.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no, use=reference
Allow: /
# Internal search results are not content: the query space is unbounded and every page of
# it is thin and duplicative. The Worker also sends X-Robots-Tag: noindex on this path —
# this rule keeps the crawl budget off it in the first place.
Disallow: /hledani

# Live-retrieval / answer-engine crawlers — explicitly welcomed so we can be cited.
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Applebot
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: Claude-User
Allow: /
User-agent: SeznamBot
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Bingbot
Allow: /
# Grounding for Gemini / AI Overviews. Retrieval, not training — see the note above.
User-agent: Google-Extended
Allow: /

# Bulk-training crawlers — refused. Nic z toho nezakazuje citaci, jen trénování.
User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: meta-externalagent
Disallow: /

Sitemap: https://informuje.me/sitemap.xml
Sitemap: https://informuje.me/sitemap-news.xml

# Strojová rozhraní / machine interfaces. The Content-Signal above governs them too:
# retrieval and citation yes, bulk training no.
# ARD (Agentic Resource Discovery) — the capability manifest, also at
# /.well-known/ai-catalog.json, which is the primary mechanism.
Agentmap: https://informuje.me/.well-known/ai-catalog.json
# MCP server (Model Context Protocol), anonymous and read-only: https://informuje.me/mcp
# What we are good for, what we are not, and how to cite us: https://informuje.me/pro-agenty