# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# AIOS Cloud — robots.txt
# https://aios-cloud.com
# Last updated: 2026-07-09

# ── Default policy ─────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/
Allow:    /wp-json/wp/v2/
Allow:    /wp-admin/admin-ajax.php

# Query-string bloat: kill duplicates from campaigns, filters, package
# routing, and cache-buster versioning. Keep clean canonical URLs indexed.
Disallow: /*?package=
Disallow: /*?topic=
Disallow: /*?utm_
Disallow: /*?gclid=
Disallow: /*?fbclid=
Disallow: /*?msclkid=
Disallow: /*?ver=
Disallow: /*?replytocom=

# Language-prefixed integration pages are noindex (same Greek body content
# as the canonical /aios-connector/{erp-eshop}/). Save crawl budget.
Disallow: /en/aios-connector/*-*/
Disallow: /zh/aios-connector/*-*/
Disallow: /bg/aios-connector/*-*/

# Legacy WP demo paths — 410 Gone anyway, don't spend crawl budget on them.
Disallow: /2020/
Disallow: /2021/
Disallow: /2022/
Disallow: /2023/
Disallow: /2024/
Disallow: /case-study/
Disallow: /category/social-media/
Disallow: /category/digital-marketing/
Disallow: /home-alternate/
Disallow: /giati-aios/

# ── AI / citation crawlers (explicitly allowed) ────────────────────
# Goal: inclusion in AI answers, model memory, and search citations.

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

User-agent: OAI-SearchBot
Allow: /

User-agent: GPTBot
Allow: /

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

User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

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

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

User-agent: Perplexity-User
Allow: /

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

User-agent: Applebot
Allow: /

# Amazon (Rufus / Alexa AI) --------------------------------------------
User-agent: Amazonbot
Allow: /

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

User-agent: FacebookBot
Allow: /

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

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

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

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

# Common Crawl (feeds many open-source models) ------------------------
User-agent: CCBot
Allow: /

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

# ByteDance (Doubao / TikTok) -----------------------------------------
User-agent: Bytespider
Allow: /

# Kagi -----------------------------------------------------------------
User-agent: Kagibot
Allow: /

# Diffbot (structured knowledge extraction) ---------------------------
User-agent: Diffbot
Allow: /

# ── Sitemaps ───────────────────────────────────────────────────────
Sitemap: https://aios-cloud.com/sitemap_index.xml