Agentic SEO (AEO) Tools

This project provides Agentic Engine Optimization (AEO) tools to audit documentation and websites, ensuring content is discoverable, parseable, and useful for AI coding agents. It targets developers and content creators aiming to improve how AI agents consume their material, preventing valuable information from being ignored.

How It Works

The tool employs a heuristic, structural analysis approach without requiring API keys. It auto-detects various web frameworks to locate build outputs. Core functionality involves file analysis (e.g., robots.txt, llms.txt, AGENTS.md, skill.md) and content analysis using Cheerio for HTML and Remark for Markdown. It measures token counts per page via gpt-tokenizer and simulates AI agent fetching to evaluate content accessibility and structure. This methodology specifically addresses AI agent consumption patterns, which differ significantly from human readers.

Quick Start & Requirements

Installation is straightforward via npm: npm install -g agentic-seo or by using npx agentic-seo directly. Prerequisites include Node.js and npm. The tool supports numerous frameworks including Next.js, Docusaurus, Hugo, Sphinx, and Vite. A npx agentic-seo init command is available to scaffold necessary AEO files. Auditing can be performed on local directories (npx agentic-seo ./my-docs-site), live URLs (npx agentic-seo --url https://docs.example.com), or via a local server (npx agentic-seo --serve ./build).

Highlighted Details

• Performs 10 checks across 5 categories: Discovery (e.g., robots-txt, llms-txt), Content Structure (semantic HTML, Markdown availability), Token Economics (page token limits, meta tags), Capability Signaling (e.g., skill.md), and UX Bridge (e.g., "Copy for AI" buttons).
• Assigns a score out of 100, translating into a grade (A-F) indicating agent readiness.
• Offers a prioritized list for AEO improvements, starting with robots.txt and llms.txt.

Maintenance & Community

The provided README does not detail specific contributors, sponsorships, or community channels (e.g., Discord, Slack).

Licensing & Compatibility

The project is released under the permissive MIT license. This license generally allows for broad compatibility with commercial use and integration into closed-source projects without significant restrictions.

Limitations & Caveats

This tool is presented as a "best-effort community offering" and provides "directional guidance, not guarantees." It is not an official Google project. Its focus is exclusively on optimizing content for AI agent consumption, not for traditional human SEO or other purposes.