# 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: /

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

# Search engines: fully allowed. Stated first and explicitly so that no
# merged/managed robots.txt block can leave them inheriting a Disallow.
User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /auth/

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /
Disallow: /api/
Disallow: /auth/

User-agent: YandexBot
Allow: /
Disallow: /api/
Disallow: /auth/

# Content Signals — https://contentsignals.org/
# Velorum lore is ours. Agents may read it to answer a visitor's question,
# and it may surface in search. It may not be scraped into training corpora.
User-agent: *
Content-Signal: ai-train=no, ai-input=yes, search=yes
Allow: /
Disallow: /api/
Disallow: /auth/

# Named AI crawlers — same rules, stated explicitly so they are unambiguous.
User-agent: GPTBot
Content-Signal: ai-train=no, ai-input=yes, search=yes
Allow: /
Disallow: /api/
Disallow: /auth/

User-agent: ClaudeBot
Content-Signal: ai-train=no, ai-input=yes, search=yes
Allow: /
Disallow: /api/
Disallow: /auth/

User-agent: PerplexityBot
Content-Signal: ai-train=no, ai-input=yes, search=yes
Allow: /
Disallow: /api/
Disallow: /auth/

User-agent: Google-Extended
Content-Signal: ai-train=no, ai-input=yes, search=yes
Allow: /
Disallow: /api/
Disallow: /auth/

User-agent: Applebot-Extended
Content-Signal: ai-train=no, ai-input=yes, search=yes
Allow: /
Disallow: /api/
Disallow: /auth/

User-agent: Bytespider
Content-Signal: ai-train=no, ai-input=yes, search=yes
Allow: /
Disallow: /api/
Disallow: /auth/

User-agent: CCBot
Content-Signal: ai-train=no, ai-input=yes, search=yes
Allow: /
Disallow: /api/
Disallow: /auth/

Sitemap: https://furai.space/sitemap.xml

# Agent surface: https://furai.space/llms.txt
# MCP server card: https://furai.space/.well-known/mcp/server-card.json

# © 2026 FURAI LAB. All rights reserved. Velorum, its characters, lore and
# portraits are proprietary. Rights of text and data mining are expressly
# reserved under Art. 4(3) of EU Directive 2019/790.
# Terms: https://furai.space/legal
# TDM reservation: https://furai.space/.well-known/tdmrep.json