# robots.txt for lakora.net
# Syntax: RFC 9309 (Robots Exclusion Protocol). Sitemap: sitemaps.org protocol.
# Content signals follow the Content Signals Policy convention. They are declared as a
# comment inside the 'User-agent: *' group below, because Content-Signal is not an
# RFC 9309 directive (strict robots.txt validators report unknown directives as errors).
#
# IMPORTANT: This file and /llms.txt must stay in sync.
# If crawler permissions change here, update the Crawler policy in llms.txt.


# --- Search engines: always allowed -------------------------------------------
User-agent: Googlebot
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: Applebot
Allow: /

# --- AI answer / retrieval agents: allowed ------------------------------------
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: MistralAI-User
Allow: /

# --- AI training / data crawlers: allowed (matches ai-train=yes) ---------------
# To opt out of AI training: Disallow these, set Content-Signal ai-train=no,
# and update the Crawler policy section in /llms.txt.
User-agent: GPTBot
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Applebot-Extended
Allow: /
User-agent: CCBot
Allow: /
User-agent: Bytespider
Allow: /
User-agent: meta-externalagent
Allow: /
User-agent: meta-externalfetcher
Allow: /
User-agent: Amazonbot
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: cohere-ai
Allow: /
User-agent: YouBot
Allow: /
User-agent: Diffbot
Allow: /
User-agent: ImagesiftBot
Allow: /
User-agent: Omgilibot
Allow: /
User-agent: Timpibot
Allow: /
User-agent: FacebookBot
Allow: /

# --- Scrapers and SEO data collectors: not permitted --------------------------
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: BLEXBot
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: serpstatbot
Disallow: /
User-agent: ZoominfoBot
Disallow: /

# --- Everything else ----------------------------------------------------------
# /data/*.json stays readable by AI agents (it is listed in /llms.txt);
# it is kept out of search indexes with an X-Robots-Tag header instead of a
# Disallow rule, so AI retrieval is not blocked.
User-agent: *
# Content-Signal: search=yes, ai-input=yes, ai-train=yes
Disallow: /cdn-cgi/
Disallow: /data/snap/
Allow: /

Sitemap: https://lakora.net/sitemap.xml