# llms.txt — Guidance for AI crawlers and model trainers
# Project: Manic Emu (manicemu.com)
# Purpose: Clarify permitted AI access, usage, and restrictions for website content
# Format: Human‑readable policy file served at /. Fallback to robots.txt still applies.

# --- Identification ---
Owner: Manic Emu
Contact: https://manicemu.com/contact
Email: support@manicemu.com
Updated: 2025-08-26
Policy-Version: 1.0
Sitemap: https://manicemu.com/sitemap.xml

# --- General Policy ---
# Public, non-login content may be accessed for indexing and search snippets subject to the
# limits and restrictions defined below. Any use for training, fine-tuning, evaluation,
# dataset creation, or derivative model building is NOT permitted without prior written consent.

Use-For: indexing, search-snippets, summarization-for-end-users
Disallow-Use: model-training, dataset-building, embeddings-at-scale, content-redistribution
Attribution-Required: yes (link back to source URL)
Commercial-Use: by-permission-only

# --- Crawl & Rate Limits ---
# Respect robots.txt and standard HTTP headers. Keep traffic reasonable.
Crawl-Delay: 10
Max-Requests-Per-Minute: 5
Max-Parallel-Requests: 2

# --- Path Rules ---
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /scripts/
Disallow: /private/
Disallow: /_next/
# Do not extract or reuse embedded game iframes or remote assets for training
Disallow: /games/* (content reuse for training)

# --- Content-Specific Guidance ---
# Allowed for snippets (<= 160 words) with attribution:
Allow-Snippets: /blog/
Allow-Snippets: /articles/
Allow-Snippets: /categories/

# Prohibited content types for training or redistribution
No-Train: all
No-Train-Reason: Copyrighted editorial content, curated guides, and licensed game media.

# --- Bot-Specific Directives ---
# Common AI crawlers. Others should follow General Policy.

User-Agent: GPTBot
Disallow: /

User-Agent: Google-Extended
Disallow: /

User-Agent: CCBot
Disallow: /

User-Agent: anthropic-ai
Disallow: /

User-Agent: PerplexityBot
Disallow: /

# --- Enforcement & Allowlist ---
# We employ bot protection (e.g., Cloudflare Bot Management, rate limiting). Non-compliant traffic
# may be blocked. For research partnerships or legitimate API-based access, request allowlisting:
# 1) Describe purpose, scope, and data retention; 2) Provide IP ranges and UA string; 3) Agree to attribution
# and non-training terms.
Allowlist-Request: https://manicemu.com/contact

# --- Compliance ---
# If your crawler cannot parse llms.txt, you must default to robots.txt and the most restrictive interpretation.
# By accessing this site, you agree to these terms. For partnership or licensing, contact us via the URL above.