🌍 E-GEO
Generative Engine Optimization (GEO) & Answer Engine Optimization (AEO) for AI-Powered Search
Get your pages cited by ChatGPT, Perplexity, Claude and Gemini.
Open-source CLI + Claude Code skills, built on published GEO research.
🌐 Website • 📊 Case study • 📖 Docs • 🐛 Issues • 💬 Discussions • 📝 Research Paper
⚡ Try it in 30 seconds
pip install egeo
GEO_EVAL_MOCK=1 egeo optimize your-page.md # any Markdown page; mock run, no API key
You get geo-output/ with a GEO score, a rewritten page, JSON-LD schema and a report. Drop GEO_EVAL_MOCK=1 and set an OpenAI-compatible key for a real run (getting started).
Already using an AI-visibility tracker? Trackers tell you where you're invisible; E-GEO fixes the page. Feed their report to egeo fix-gaps and it rewrites each page that loses a query:
geo citations --brand "Acme" --domain acme.com --format json --output gaps.json # or any tracker's CSV/JSON export
egeo fix-gaps gaps.json --project project.yaml --dry-run # see which pages it would rewrite
(fix-gaps reference)
Does it work? We measure it on ourselves every week: a fixed set of 10 queries in Perplexity. E-GEO was cited in 3/10 answers for weeks; the 2026-09-21 snapshot reached 5/10, including generic queries like "open source AEO tools" (one snapshot, not yet a trend). Method and earlier snapshots: public case study.
⭐ If this is useful, hit Star at the top of this page — it is how other developers (and answer engines) find it.
✨ What is E-GEO?
E-GEO is an open-source Generative Engine Optimization (GEO) and Answer Engine Optimization (AEO) toolkit that transforms your website content to rank higher in AI-powered search engines — including ChatGPT, Perplexity, Google AI Overviews, Claude, and Gemini.
Also known as AI SEO or LLM SEO, GEO is the practice of optimizing content so that generative AI engines can crawl, understand, cite, and recommend it. E-GEO automates this entire process.
Based on the E-GEO research preprint (arXiv:2511.20867), it applies 10 research-derived features — including competitive framing, citation optimization, structured data, and semantic density improvements — as documented in the paper's experiments.
- ✅ No learning curve — One command to optimize
- ✅ Research-backed — Based on published GEO research
- ✅ Production-ready — Copy-paste optimized content
- ✅ Multi-engine — Optimizes for ChatGPT, Perplexity, Gemini, Claude & Google AI Overviews
- ✅ Full pipeline — Analyze → Rank → Rewrite → Schema in one command
/geo https://yoursite.com/pricing
↓
geo-output/
├── report.md
├── optimized/
│ └── pricing.md
└── schema/
└── pricing.json
📈 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 GEO tool?"
ChatGPT: "According to [Competitor], the best tool is..."
↑ They get cited. You don't.
- ChatGPT 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 study on GPT-4).
- 844,000+ sites already ship an
llms.txt. Is yours one of them?
Traditional SEO optimizes for blue links. GEO optimizes for citations in AI-generated answers. E-GEO is the open-source tool that bridges this gap.
🚀 Quick Start (3 Steps)
1. Install
Copy the .claude/ folder to your project:
cp -r /path/to/eGEOagents/.claude .
2. Activate
In Claude Code, switch to GEO mode:
/output-style geo-optimizer
3. Optimize
Run your first optimization:
/geo https://yoursite.com
🧩 Install as Skills (skills.sh)
Install the complete skill collection:
npx skills add https://github.com/mverab/eGEOagents
Install one skill only:
npx skills add https://github.com/mverab/eGEOagents --skill competitive-analysis
Validate parser discovery before shipping updates:
npx skills add https://github.com/mverab/eGEOagents --list
Verify indexing pages:
📋 Commands
| Command | What it does |
|---|
/geo <url> | Full pipeline - Analyze, rank, rewrite, schema |
/geo:audit <url> | Analysis only, no changes |
/geo:optimize <file> | Optimize local content file |
/geo:batch <folder> | Process entire folder |
/geo:report | Generate executive report |
/geo:compete <query> | Competitive analysis |
/geo:loop <domain> | One bounded loop-mode iteration over a workspace domain |
📊 What You Get
After running /geo:
geo-output/
├── report.md # Executive summary + scores
├── analysis.json # Raw analysis data
├── optimized/
│ └── pricing.md # Rewritten content (ready to use)
├── schema/
│ └── pricing.json # JSON-LD markup (copy to site)
└── checklist.md # Step-by-step implementation
This is the beginning of the README. Read the rest at the original. Read the full README ↗
