# ============================================
# ROBOTS.TXT - AI & Search Engine Crawler Rules
# PolymarketScan - Polymarket Data Platform
# ============================================

# ----- Content Signals (AI usage preferences) -----
# Maximally permissive: allow search indexing, AI training, and AI inference inputs.
# Also emitted as the Content-Signal HTTP response header (see vercel.json / public/_headers).
Content-Signal: search=yes, ai-train=yes, ai-input=yes

# PolymarketScan is a free public good: no paywall, no signup, no metering on any page.
# Citing, linking, and sharing our pages in AI answers is encouraged — distribution is
# how a free product is supported. Machine-readable details: /llms.txt (see also
# isAccessibleForFree in per-page structured data and CC BY 4.0 on market data pages).

# ----- AI Engine Crawlers - Explicitly Allow -----
# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# OpenAI Search (cited answers in ChatGPT search)
User-agent: OAI-SearchBot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: Claude-SearchBot
Allow: /

# xAI / Grok
User-agent: Grok
Allow: /

User-agent: GrokBot
Allow: /

# Google AI (Gemini, Bard, AI Overviews)
User-agent: Google-Extended
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Microsoft / Copilot
User-agent: Bingbot
Allow: /

# You.com AI
User-agent: YouBot
Allow: /

# Brave Search AI
User-agent: BraveBot
Allow: /

# DeepSeek AI
User-agent: DeepSeekBot
Allow: /

# Mistral AI
User-agent: MistralAI-User
Allow: /

# DuckDuckGo AI Assistant
User-agent: DuckAssistBot
Allow: /

# Amazon / Alexa AI
User-agent: Amazonbot
Allow: /

# ByteDance / TikTok AI
User-agent: Bytespider
Allow: /

# AI agent crawlers / autonomous agents
User-agent: AutoGPT
Allow: /

User-agent: OpenClaw
Allow: /

# Common Crawl (training corpus)
User-agent: CCBot
Allow: /

# ----- Traditional Search Engine Crawlers -----
User-agent: Googlebot
Allow: /

User-agent: Yandex
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

# ----- Default Rule for All Other Crawlers -----
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/internal/
Disallow: /~api/
Disallow: /~flock.js
Disallow: /partners/

# ----- Agent Discovery Files -----
# These files help AI agents and LLMs discover our API:
# /ai.txt             - AI usage permissions (inference, indexing, training)
# /skill.md           - Full API documentation (machine-readable)
# /llms.txt           - LLM-optimized site summary
# /agents.json        - Structured API metadata for agent frameworks
# /.well-known/ai-plugin.json - OpenAI plugin manifest

# ----- Sitemap Location -----
Sitemap: https://sitemap.polymarketscan.org/sitemap-index.xml