# See http://www.robotstxt.org/robotstxt.html for documentation on how to use the robots.txt file

User-agent: *
Allow: /

# Disallow admin and private areas
Disallow: /admin/
Disallow: /auth/
Disallow: /api/
Disallow: /*?*session*
Disallow: /*?*utm*

# Allow crawling of important static files
Allow: /images/
Allow: /assets/
Allow: /*.css
Allow: /*.js
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /.well-known/ai-plugin.json
Allow: /.well-known/agent.json
Allow: /.well-known/api-catalog
Allow: /.well-known/mcp/server-card.json
Allow: /.well-known/agent-skills/
Allow: /.well-known/oauth-authorization-server
Allow: /.well-known/ucp
Allow: /.well-known/acp.json

# Content Signals - AI content usage preferences
# See https://contentsignals.org/
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Sitemap location
Sitemap: https://www.deployhq.com/sitemap.xml

# Sitemap (Markdown variant for AI agents and LLM crawlers)
Sitemap: https://www.deployhq.com/sitemap-md.xml

# AI Search Crawlers (explicitly allowed with same restrictions as *)
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: cohere-ai
Allow: /
Disallow: /admin/
Disallow: /auth/
Disallow: /api/
Disallow: /*?*session*
Disallow: /*?*utm*
# Repeat the content usage preferences here: a crawler obeys only its most
# specific matching group, so these named AI crawlers do not inherit the
# Content-Signal declared under User-agent: *.
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Crawl-delay for specific bots (optional)
User-agent: Bingbot
Crawl-delay: 2