geo-optimizer-skill

The open-source Answer Engine Optimization (AEO) & Generative Engine Optimization (GEO) toolkit.

Audit, optimize, and track whether ChatGPT, Perplexity, Gemini, Claude, and Google AI Overviews can crawl, understand, and cite your website.

One command scores your site 0–100 on AI-search readiness, tells you exactly what to fix, and checks whether AI engines actually cite you.

Quick Start · Live Demo · Pricing · Sign Up · Documentation · Changelog

16 CLI commands · 8 scoring categories · 47 research-backed methods · 7 output formats · 1,900+ tests · academic foundation (KDD 2024, ICLR 2026) · runs in CI/CD, as a Python library, an MCP server, or an Astro integration

What is GEO Optimizer?

GEO Optimizer measures how visible your website is to AI answer engines — ChatGPT, Perplexity, Google AI Overviews, Gemini, and Claude — scores it 0–100, and tells you exactly what to fix to get cited. It is free and open source, and runs as a command-line tool, a Python library, an MCP server, or an Astro integration.

This practice goes by several names — Answer Engine Optimization (AEO), Generative Engine Optimization (GEO), AI SEO, LLM SEO, AI Search Optimization — and GEO Optimizer covers all of them under one command. Several of its checks (schema markup, meta tags, canonical URLs, Open Graph, content structure) are standard technical SEO practice too, audited alongside the AI-specific ones. If you're searching for an "open-source AEO tool", a "tool to check if ChatGPT cites my website", or a "technical SEO and llms.txt checker" — that's this.

# Zero install — score any site against 8 AI-readiness categories
uvx --from geo-optimizer-skill geo audit --url https://yoursite.com

It scores your site against 47 research-backed methods (Princeton KDD 2024, AutoGEO ICLR 2026) and generates the exact fixes — robots.txt bot rules, llms.txt, JSON-LD schema, and the content patterns models quote.

Why AI visibility matters in 2026

AI search engines give one synthesized answer and cite a handful of sources. If your site isn't one of them, you're invisible — even if you rank #1 on Google.

User asks ChatGPT: "What's the best mortgage calculator?"

ChatGPT: "According to [Competitor.com], the formula is..."
          ↑ They get cited. You don't.

• ChatGPT alone serves 900M weekly users — a growing share of sessions that used to be Google searches.
• 28.3% of ChatGPT's most-cited pages have zero organic visibility on Google (Ahrefs) — AI engines reward different signals than classic SEO.
• Proper JSON-LD schema lifts LLM extraction accuracy from 16% to 54% (Semrush test on GPT-4).
• 844,000+ sites already ship an llms.txt. Yours?
• Our own State of GEO benchmark, run monthly across 1,000+ real sites with this same engine, finds a median score of 57/100 — most sites audited are still unprepared, and only 57% ship an llms.txt.

Does AI actually cite your brand? Ask it directly.

geo citations queries real answer engines with the questions your customers ask, then reports whether your brand is mentioned and your domain is cited as a source — and which competitors get cited instead of you.

AEO / GEO is not traditional SEO

SEO and AEO/GEO answer different questions:

• SEO optimizes for ranking and clicks in traditional search result pages — crawlability, backlinks, keyword signals.
• AEO / GEO measures whether an AI answer engine can read, parse, understand, and cite your content when generating a response.
• A site can rank well on Google and still be largely opaque to AI systems — missing structured data, no llms.txt, bot access blocked, thin factual density.

GEO Optimizer focuses on the technical and structural signals AI answer engines use: robots.txt bot permissions, llms.txt presence and depth, JSON-LD schema richness, brand entity coherence, multi-page topical authority, and content citability across 47 methods.

Try it online

Open-source vs GeoReady Platform

The CLI and web audit remain MIT-licensed and free. The GeoReady platform adds server-side continuity — monitoring, history, and team features — that a local CLI cannot provide on its own.

Quick Start

pip install geo-optimizer-skill

No install? One-shot audit with uv:

uvx --from geo-optimizer-skill geo audit --url https://yoursite.com

# Audit any site — get a score 0-100 with actionable recommendations
geo audit --url https://yoursite.com

# Audit a full sitemap and surface weakest pages first
geo audit --sitemap https://yoursite.com/sitemap.xml --max-urls 25

# Compare before/after versions of a page
geo diff --before https://yoursite.com/page-old --after https://yoursite.com/page-new

# Save history and detect regressions over time
geo audit --url https://yoursite.com --save-history --regression

# Show the saved trend for a site
geo history --url https://yoursite.com

# What changed since the last snapshot? (severity + category deltas; CI: --fail-on warning)
geo drift --url https://yoursite.com

# Passive AI visibility snapshot for a domain
geo monitor --domain yoursite.com

# Ask real AI engines: is my brand mentioned? Is my domain cited as a source?
# BYO API key — PERPLEXITY_API_KEY recommended (real web citations)
geo citations --brand "YourBrand" --domain yoursite.com --topic "your product category"

# AI answers vary run to run — sample each query 5x for a confidence interval
geo citations --brand "YourBrand" --domain yoursite.com --runs 5

# Save or query archived AI answer snapshots
geo snapshots --query "best GEO tool" --from 2026-03-01 --to 2026-03-30

# Score citation quality inside an archived answer snapshot
geo snapshots --quality --snapshot-id 12 --target-domain yoursite.com

# Run recurring monitoring and generate an HTML trend report
geo track --url https://yoursite.com --report --output ./geo-track-report.html

# Auto-generate all missing files (robots.txt, llms.txt, schema, meta)
geo fix --url https://yoursite.com --apply

# Generate llms.txt from sitemap
geo llms --base-url https://yoursite.com --output ./public/llms.txt

# Check whether an existing llms.txt still matches the current sitemap
# (exits 1 on stale URLs — CI-gateable, no per-link HTTP request)
geo llms --base-url https://yoursite.com --check-drift

# Generate JSON-LD schema
geo schema --type faq --url https://yoursite.com

geo citations also supports MiniMax, Gemini, and DeepSeek as providers — including MiniMax's regional API roots and dual wire formats, and DeepSeek's coverage of the Chinese AI answer-engine ecosystem. Full setup for each: docs/llm-providers.md.

Google AI Overviews isn't an LLM you can prompt — it's a SERP feature — so --provider serpbase observes the real Google SERP directly (organic results + the AI Overview block, when Google renders one) via serpbase.dev instead of inferring it through a Gemini API key. Opt-in, bring-your-own-key: 100 free searches, then $0.30/1k.

export SERPBASE_API_KEY=...
geo citations --brand "YourBrand" --domain yoursite.com --provider serpbase

What it checks

Score bands: 86-100 Excellent · 68-85 Good · 36-67 Foundation · 0-35 Critical

Bonus checks (informational, do not affect score):