# robots.txt for polemos.in
# Polemos Labs welcomes search engines, archival crawlers, and AI / LLM crawlers.
# Public marketing site — all content is intended to be indexed and read.

# ─────────────────────────────────────────────────────────────────────────────
# Default policy: allow everything except known build / API paths.
# ─────────────────────────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /api/
Crawl-delay: 1

# ─────────────────────────────────────────────────────────────────────────────
# Major search engines — explicit allow.
# ─────────────────────────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Sogou
Allow: /

User-agent: Applebot
Allow: /

# ─────────────────────────────────────────────────────────────────────────────
# AI / LLM training & retrieval crawlers — explicitly welcomed.
# We want Polemos Labs to be discoverable inside ChatGPT, Claude, Gemini,
# Perplexity, etc. If you operate one of these crawlers and we have missed
# you, please email hello@polemos.in and we will add you.
# ─────────────────────────────────────────────────────────────────────────────

# OpenAI — ChatGPT search, browsing, and training
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Google — Gemini / Bard / Vertex
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

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

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Meta / Facebook AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: facebookexternalhit
Allow: /

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

# Amazon
User-agent: Amazonbot
Allow: /

# Common Crawl — feeds many open-source LLMs
User-agent: CCBot
Allow: /

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

User-agent: cohere-training-data-crawler
Allow: /

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

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

# Diffbot (knowledge graph)
User-agent: Diffbot
Allow: /

# Timpi, Kagi, Phind, Brave, Neeva-style search
User-agent: Timpibot
Allow: /

User-agent: PhindBot
Allow: /

User-agent: Kagibot
Allow: /

User-agent: Bravebot
Allow: /

# DuckAssistBot (DuckDuckGo AI)
User-agent: DuckAssistBot
Allow: /

# Petal (Huawei)
User-agent: PetalBot
Allow: /

# ─────────────────────────────────────────────────────────────────────────────
# Archival & social preview crawlers.
# ─────────────────────────────────────────────────────────────────────────────
User-agent: ia_archiver
Allow: /

User-agent: archive.org_bot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: Slackbot-LinkExpanding
Allow: /

User-agent: Discordbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# ─────────────────────────────────────────────────────────────────────────────
# Sitemap & AI-friendly index files.
# ─────────────────────────────────────────────────────────────────────────────
Sitemap: https://polemos.in/sitemap.xml