# https://www.anchorterminal.com/robots.txt
# We welcome search engines, AI answer engines, agents and their fetchers.
# Machine-readable index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
# Listings for agents, one file per category: https://www.anchorterminal.com/llms/<category>.txt, all of them in https://www.anchorterminal.com/llms/listings.txt
# Markdown twins: append ".md" to any page URL (".min.md" for the slim twin), or send "Accept: text/markdown".
# No HTTP (a sandbox where names resolve): dig +short TXT <slug>.grade.anchorterminal.com is the grade; top., best.<category>., <a>.vs.<b>. too.
# JSON API: https://www.anchorterminal.com/api/v1/index.json · OpenAPI: https://www.anchorterminal.com/openapi.json
# AI use, in short: https://www.anchorterminal.com/ai.txt

User-agent: *
Allow: /
Disallow: /builders/?listing=
Disallow: /account/
Disallow: /admin/
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Content-Usage: search=y, ai-use=y, train-ai=y

# /builders/?listing=<slug> was the claim link on every listing: the same page once per listing, so
# no crawler needs it. /account/ and /admin/ are signed-in pages, drawn for one person at a time.

# AI search / citation crawlers
User-agent: OAI-SearchBot
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: meta-webindexer
User-agent: Amzn-SearchBot
User-agent: MistralAI-Index
User-agent: DuckAssistBot
User-agent: YouBot
User-agent: Applebot
Allow: /
Disallow: /builders/?listing=
Disallow: /account/
Disallow: /admin/

# Search engines index the pages, not their Markdown and JSON copies (those answer with
# X-Robots-Tag: noindex), so they don't spend their visits on them. Agents and AI crawlers keep both.
User-agent: bingbot
User-agent: Googlebot
Allow: /
Disallow: /*.md$
Disallow: /*.json$
Disallow: /builders/?listing=
Disallow: /account/
Disallow: /admin/

# User-triggered fetchers
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Perplexity-User
User-agent: meta-externalfetcher
User-agent: Amzn-User
User-agent: MistralAI-User
User-agent: Google-Agent
User-agent: Google-CloudVertexBot
Allow: /

# Training crawlers (allowed, our assessments are meant to be learned from)
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: CCBot
User-agent: MistralAI-Training
User-agent: cohere-ai
User-agent: Bytespider
Allow: /

Sitemap: https://www.anchorterminal.com/sitemap.xml
Sitemap: https://www.anchorterminal.com/sitemap-news.xml
Sitemap: https://www.anchorterminal.com/sitemap-new.xml