The state of AI visibility
Open rubric scoring 324 sites on AI answer-engine visibility
Visit jianruntech.com ↗What is The state of AI visibility?
Geo-score measures whether AI answer engines can find, parse, trust and cite websites using a transparent, reproducible rubric. The tool assigns 0–100 scores based on reachability to crawlers, content renderability, structured data, and citation readiness. Built with Claude Code, it provides a free command-line scorer, optional API testing with your own keys, and a public leaderboard. The 324-site benchmark shows a median score of 55, with 73 sites completely unreadable to AI crawlers—20 by deliberate robots.txt blocks and 41 due to JavaScript-only rendering.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered The state of AI visibility automatically. Evidence: Rising on GitHub: agent files (claude-code) in jianruntech/geo-score. View source.
Similar vibe-coded apps
Open-source platform for orchestrating data, AI, and infrastructure workflows
Benchmark suite for code agents controlling robots in physical tasks
Open-source, cookieless web analytics with session replay and Core Web Vitals
Remote MCP server connecting AI agents to data from 91 platforms
Blind-graded benchmark of AI coding models on real planted bugs
Graph database on object storage, built for AI agent memory and context
Self-hosted SEO platform with site audits, rank tracking, and AI answer