# RJL.ai Robots.txt
# https://rjl.ai/

# Default policy: allow all general-purpose crawlers
User-agent: *
Allow: /
Disallow: /cgi-bin/

# ----------------------------------------------------------
# AI training and answer-engine crawlers
# Stance: ALLOW indexing and citation by AI assistants and
# answer engines. Block private paths only.
# See also: /llms.txt for a curated content map.
# ----------------------------------------------------------

# OpenAI - ChatGPT browsing and search
User-agent: GPTBot
Allow: /
Disallow: /cgi-bin/

User-agent: OAI-SearchBot
Allow: /
Disallow: /cgi-bin/

User-agent: ChatGPT-User
Allow: /
Disallow: /cgi-bin/

# Anthropic - Claude
User-agent: ClaudeBot
Allow: /
Disallow: /cgi-bin/

User-agent: Claude-Web
Allow: /
Disallow: /cgi-bin/

User-agent: anthropic-ai
Allow: /
Disallow: /cgi-bin/

# Google - Gemini / AI Overviews / Bard
User-agent: Google-Extended
Allow: /
Disallow: /cgi-bin/

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /cgi-bin/

User-agent: Perplexity-User
Allow: /
Disallow: /cgi-bin/

# You.com
User-agent: YouBot
Allow: /
Disallow: /cgi-bin/

# Common Crawl (feeds many AI training datasets)
User-agent: CCBot
Allow: /
Disallow: /cgi-bin/

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /
Disallow: /cgi-bin/

User-agent: FacebookBot
Allow: /
Disallow: /cgi-bin/

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Disallow: /cgi-bin/

# ByteDance / TikTok
User-agent: Bytespider
Allow: /
Disallow: /cgi-bin/

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /
Disallow: /cgi-bin/

# Mistral
User-agent: MistralAI-User
Allow: /
Disallow: /cgi-bin/

# Cohere
User-agent: cohere-ai
Allow: /
Disallow: /cgi-bin/

# Sitemap location
Sitemap: https://rjl.ai/sitemap.xml