geo-score

Can AI engines cite your site, and do they? Free 0–100 readiness score on an open GEO rubric, plus ask and weekly citation tracking via OpenAI, Perplexity, Gemi

What is geo-score?

Can AI engines cite your site, and do they? Free 0–100 readiness score on an open GEO rubric, plus ask and weekly citation tracking via OpenAI, Perplexity, Gemini, Anthropic and OpenRouter with your own keys. Zero dependencies; CLI, GitHub Action and MCP server.

Overview of geo-score

What it is

geo-score is an open-source AI visibility (GEO) scorer for websites, by Jianrun Tech (见润科技). It scores a website from 0 to 100 on whether AI answer engines can reach it, parse it, trust it and cite it, against a published, versioned rubric. With your own API keys, it also asks the engines the questions your buyers ask and records whom the answers cite. The score is free and needs nothing installed; the citation results are reported beside it and never added to it. Formerly geo-watch, which merged into geo-score in 1.2.0 and lives on as its levels 2 and 3. The current release is geo-score==1.8.3 on PyPI. The rubric is versioned separately, and v1.1 is current. Zero dependencies; CLI, GitHub Action and MCP server.

Key features

  • Score (level 1): 21 tiered checks in five pillars, three gates, the biggest gaps first, and what each next tier needs. One file, standard library only, no key.
  • Ask (level 2): Puts one question to ChatGPT, Perplexity, Gemini and Claude through their search-enabled APIs, with your keys, and reports whom each answer cites.
  • Watch (level 3): A fixed question set, week over week: cited rate with a 95% interval, share of voice, the sources the engines lean on, and a diff that calls a change a change only when a paired test says so.
  • Reports and diffs: Text, JSON against a published schema, SARIF and JUnit; diff compares two reports check by check, and --baseline re-scores the same pages.
  • MCP server: All three levels as tools for agents over stdio; --read-only gives a server that cannot spend.
  • GitHub Action: Scores on every push, fails the build on a regression or a gate at zero, and writes a job summary.
  • Badge: An optional SVG, or shields.io endpoint JSON, with your score and band. It never moves a score or a leaderboard place.
  • Claude Code skill: The CLI, plus the three checks that need off-site search or human judgement.

Use cases

  • Checking whether AI answer engines can reach, parse, trust and cite a website.
  • Identifying mechanical and cheap-to-fix issues like a robots.txt line, a JSON-LD block, a date in a template, or a paragraph that needs rewriting.
  • Tracking how often a site is cited by AI engines against competitors and sources, week over week.
  • Integrating GEO scoring into CI/CD pipelines via GitHub Action or MCP server.

Getting started

See the repository README for installation and quick-start commands.

License and pricing

The license is MIT. The pricing type is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/jianruntechgeo-score.svg)](https://yunodb.com/tools/jianruntechgeo-score?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/jianruntechgeo-score?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/jianruntechgeo-score.svg" alt="Featured on YunoDB" height="20"></a>