# robots2.txt — Community Baseline Policy
# meta: spec-version: 2.0
# meta: last-update: 2026-04-06 10:00 UTC
# meta: update-frequency: monthly
# meta: significant-change: no
# meta: authored-by: robotsv2.org community
# meta: contact: baseline@robotsv2.org
# meta: jurisdiction: international
# meta: licence: CC0-1.0
# ─────────────────────────────────────────
# WHAT THIS FILE IS
#
# This is the community-maintained baseline policy for robots2.txt.
# It represents reasonable defaults that protect site owners while
# allowing legitimate AI use.
#
# HOW TO USE IT
#
# Add this as the last line of YOUR robots2.txt:
#   chain: https://robotsv2.org/community-baseline.txt
#
# Your local directives always override this file.
# This file only fills in gaps — directives you haven't set.
# Think of it as sensible defaults, not mandatory rules.
#
# If you disagree with any baseline value, just set it yourself
# in your own robots2.txt. Your file wins. Always.
# ─────────────────────────────────────────

# ══════════════════════════════════════════
# BASELINE AI POLICY
# These are the community-agreed reasonable defaults.
# Conservative by design — when in doubt, protect the creator.
# ══════════════════════════════════════════

crawl: yes
read: yes
summarise: yes
quote: short-only
derivative: no
train: no
store: session-only
compete: no
personalise: no
monetise: no

# ══════════════════════════════════════════
# BASELINE BEHAVIOUR
# ══════════════════════════════════════════

attribution: required
link-back: preferred
rate: polite
announce: yes
honest: yes

# ══════════════════════════════════════════
# BASELINE AGENT POLICIES
# ══════════════════════════════════════════

[agent: search-indexer]
crawl: yes
read: yes
summarise: yes
quote: short-only
train: no
attribution: required

[agent: ai-assistant]
crawl: yes
read: yes
summarise: yes
quote: short-only
derivative: no
train: no
monetise: no
attribution: required
link-back: preferred

[agent: ai-researcher]
crawl: yes
read: yes
summarise: yes
derivative: ask
train: no
attribution: required
link-back: required

[agent: code-assistant]
crawl: yes
read: yes
quote: yes
derivative: yes
train: no
attribution: preferred

[agent: content-generator]
crawl: no
read: no
derivative: no
train: no
# the baseline position is: content generators should not
# consume other people's content without explicit permission
# site owners who want to allow this can override locally

[agent: data-harvester]
crawl: no
read: no
store: no
# bulk data collection is opt-in, not opt-out

[agent: ad-network]
crawl: no
read: no
personalise: no
monetise: no
store: no

[agent: monitoring]
crawl: yes
read: no
store: no

# ─────────────────────────────────────────
# PHILOSOPHY
#
# The baseline follows three principles:
#
# 1. READING IS FREE, TAKING IS NOT
#    Agents can read and summarise. They cannot train on,
#    monetise, or build derivatives from content by default.
#
# 2. CREDIT THE CREATOR
#    Attribution is always required. Link-backs are preferred.
#    If you use someone's work, say so.
#
# 3. SILENCE MEANS NO
#    If a site owner hasn't said yes, assume no.
#    If the ask endpoint doesn't exist, assume deny.
#    If in doubt, don't.
#
# These defaults protect creators while keeping the web useful.
# They can be loosened by any site owner at any time.
# They should never need to be tightened.
# ─────────────────────────────────────────
# END OF COMMUNITY BASELINE
# robotsv2.org — Matthew, Claude & Gemini — maintained by the community, for the community
# ─────────────────────────────────────────