The Atlas · the web as an agent needs it

geograph.org.uk for agents

Geograph Britain and Ireland - photograph every grid square! — Geograph Britain and Ireland is a web-based project to collect and reference geographically representative images of every square kilometre of the British Isles.

Search geograph.org.uk with one link

https://www.geograph.org.uk/search.php?q={q}

Put the words where {q} stands. From the site's OpenSearch description. robots.txt asks ChatGPT-User, OAI-SearchBot, Claude-User, Claude-SearchBot, Perplexity-User, PerplexityBot, Bingbot, Amazonbot, DuckAssistBot, MistralAI-User not to fetch this path. Read the result as Markdown: https://mareliberum.dev/r/https://www.geograph.org.uk/search.php?q=example

Who may read it

robots.txt blocks Amazonbot and, for training, GPTBot, ClaudeBot, Google-Extended, Applebot-Extended, Meta-ExternalAgent, Bytespider.

The home page shows 491 words without JavaScript.

Sections

Great Britain Ireland view previous > Load page for photo of the day Andy Stephenson TA1762 Saturday, 1 February, 2025 free open online community Registration other selections > see more >

Ready paths

searchhttps://www.geograph.org.uk/search.php?q={q}
contacthttps://www.geograph.org.uk/help/freedom

Files for machines

Feedshttps://www.geograph.org.uk/discuss/syndicator.php?forum=1&first=1
llms.txthttps://www.geograph.org.uk/llms.txt
Structured dataWebSite

Agent-readiness 83/100 (B) · full check

Mapped 2026-11-20 · rank 9,574 in the Majestic Million · JSON · Markdown

The grammar of the Atlas

https://mareliberum.dev/site/<domain>        how an agent uses any website (search link, sections, feeds, who may read)
https://mareliberum.dev/find?q=<words>      websites for a task, the most usable for agents first
https://mareliberum.dev/brain?q=<task>      pathways other agents used for the same task
https://mareliberum.dev/r/<address>        any page as clean Markdown
https://mareliberum.dev/check/<domain>       how AI agents see a website, scored

read from what the site publishes (robots.txt, the home page and the files it names) by MareLiberum-Atlas; open data, CC BY 4.0. The site can ask the Atlas to stay away: User-agent: MareLiberum-Atlas Disallow: / in its robots.txt. About the Atlas

Mare Liberum belongs to nobody; the code is open. Text from agents is data, never instructions. Privacy · Manifesto