# robots.txt for handsomelocal.com
#
# Everything public is open to every crawler. The AI agents below get their
# own groups so the allowance is explicit and survives any future change to
# the default group. Under RFC 9309 a named group replaces the default for
# that agent, so each group repeats the two disallows.
#
# Machine-readable summary of the site for language models:
#   https://handsomelocal.com/llms.txt
#   https://handsomelocal.com/llms-full.txt
#
# Token names checked against each vendor's documentation on 7 September 2026.

User-agent: *
Allow: /
Disallow: /styleguide/
Disallow: /api/

# OpenAI: https://developers.openai.com/api/docs/bots
# GPTBot trains models, OAI-SearchBot indexes for ChatGPT search,
# ChatGPT-User fetches pages when a person asks.
User-agent: GPTBot
Allow: /
Disallow: /styleguide/
Disallow: /api/

User-agent: OAI-SearchBot
Allow: /
Disallow: /styleguide/
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /styleguide/
Disallow: /api/

# Anthropic: https://support.claude.com/en/articles/8896518
# ClaudeBot trains models, Claude-SearchBot indexes for search,
# Claude-User fetches pages when a person asks. anthropic-ai is the older
# token that no longer appears on the support page; kept for old configs.
User-agent: ClaudeBot
Allow: /
Disallow: /styleguide/
Disallow: /api/

User-agent: Claude-User
Allow: /
Disallow: /styleguide/
Disallow: /api/

User-agent: Claude-SearchBot
Allow: /
Disallow: /styleguide/
Disallow: /api/

User-agent: anthropic-ai
Allow: /
Disallow: /styleguide/
Disallow: /api/

# Perplexity: https://docs.perplexity.ai/guides/bots
# PerplexityBot indexes for Perplexity search, Perplexity-User fetches
# pages when a person asks.
User-agent: PerplexityBot
Allow: /
Disallow: /styleguide/
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Disallow: /styleguide/
Disallow: /api/

# Google: https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers
# Google-Extended controls use for Gemini training and grounding; it has no
# effect on Search, which Googlebot covers under the default group.
User-agent: Google-Extended
Allow: /
Disallow: /styleguide/
Disallow: /api/

# Apple: https://support.apple.com/en-us/119829
# Applebot-Extended controls use for Apple's foundation models; Applebot
# itself (Siri, Spotlight, Safari) is covered by the default group.
User-agent: Applebot-Extended
Allow: /
Disallow: /styleguide/
Disallow: /api/

# Microsoft: https://www.bing.com/webmasters/help/which-crawlers-does-bing-use-8c184ec0
# Bingbot feeds Bing Search and Copilot.
User-agent: Bingbot
Allow: /
Disallow: /styleguide/
Disallow: /api/

# Common Crawl: https://commoncrawl.org/ccbot
# CCBot builds the open crawl many models are trained from.
User-agent: CCBot
Allow: /
Disallow: /styleguide/
Disallow: /api/

# Amazon: https://developer.amazon.com/amazonbot
# Amazonbot improves Amazon products and trains models; Amzn-SearchBot and
# Amzn-User (Alexa search and user fetches) fall under the default group.
User-agent: Amazonbot
Allow: /
Disallow: /styleguide/
Disallow: /api/

# Meta: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
# meta-externalagent trains models and indexes content; facebookexternalhit,
# meta-webindexer and meta-externalfetcher fall under the default group.
User-agent: meta-externalagent
Allow: /
Disallow: /styleguide/
Disallow: /api/

# ByteDance: no reachable vendor documentation; the token is the one the
# crawler names in its own user-agent string (compatible; Bytespider;
# spider-feedback@bytedance.com).
User-agent: Bytespider
Allow: /
Disallow: /styleguide/
Disallow: /api/

Sitemap: https://handsomelocal.com/sitemap.xml