400 mTwilight zone
The Atlas · the web as an agent needs it
github.com for agents
GitHub · Change is constant. GitHub keeps you ahead. · GitHub · GitHub — Join the world's most widely adopted, AI-powered developer platform where millions of developers, businesses, and the largest open source community build software that advances humanity.
Search github.com with one link
https://github.com/search?q={q}&ref=opensearchPut 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, Googlebot, Amazonbot, DuckAssistBot, MistralAI-User not to fetch this path. Read the result as Markdown: https://mareliberum.dev/r/https://github.com/search?q=example&ref=opensearch
Who may read it
Every assistant and AI search crawler may read it; for training robots.txt blocks Bytespider.
The home page shows 428 words without JavaScript.
Sections
Build with Copilot Integrations Trending repos GitHub Sponsors Developer articles Enterprises Team Startups Nonprofits Healthcare Financial services Manufacturing
Ready paths
| search | https://github.com/search?q={q}&ref=opensearch |
Files for machines
Agent-readiness 75/100 (B) · full check
Mapped 2026-11-20 · rank 10 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