# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# robots.txt — Early Signal Arbitrage Research Hub
# https://earlysignalarbitrage.com
# Last updated: 2026-04-27

# -------------------------------------------------------
# General crawlers
# -------------------------------------------------------
User-agent: *
Allow: /
Disallow: /src/
Disallow: /_vite/
Crawl-delay: 1

# -------------------------------------------------------
# Google — standard + extended crawlers
# -------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Extended
Allow: /

User-agent: Googlebot-Image
Allow: /

# -------------------------------------------------------
# OpenAI / ChatGPT
# -------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

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

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# -------------------------------------------------------
# Perplexity AI
# -------------------------------------------------------
User-agent: PerplexityBot
Allow: /

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

# -------------------------------------------------------
# Meta AI
# -------------------------------------------------------
User-agent: FacebookBot
Allow: /

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

User-agent: bingbot
Allow: /

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

User-agent: Applebot-Extended
Allow: /

# -------------------------------------------------------
# Common research & AI crawlers
# -------------------------------------------------------
User-agent: cohere-ai
Allow: /

User-agent: CCBot
Allow: /

User-agent: DataForSeoBot
Allow: /

# -------------------------------------------------------
# Agentic discovery endpoints
# -------------------------------------------------------
# NLWeb agent manifest
# https://earlysignalarbitrage.com/.well-known/nlweb.json

# MCP resource server manifest
# https://earlysignalarbitrage.com/.well-known/mcp.json

# Machine-readable identity (llms.txt)
# https://earlysignalarbitrage.com/llms.txt

# -------------------------------------------------------
# Sitemaps
# -------------------------------------------------------
Sitemap: https://earlysignalarbitrage.com/sitemap.xml