AEO Toolkit
An open-source suite that audits whether AI answer engines can find, parse and cite a site: five free browser tools, a Chrome extension, three hosted MCP servers, and the paid audit behind our own service.
What it is
AEO Toolkit is a TypeScript monorepo for answer-engine optimization (AEO / GEO): structuring a site so ChatGPT, Perplexity, Claude and AI Overviews cite it rather than just rank it. Ten tools in total — five free browser tools at advancelabs.dev/tools, a Chrome extension (AEO/GEO Auditor), and three hosted MCP servers (ai-visibility, backlink, search) exposing 31 tools to Claude or any MCP client. Eleven packages are Apache-2.0 and published to npm on their own, including the scoring engine itself.
Why we built it
Our own AEO audit service ($750-1,500, 3-day turnaround) runs on this engine — the toolkit is the product our paid service is built from, not a lead magnet built around it. Dogfooding is explicit in its own README: advancelabs.dev ships llms.txt, JSON-LD Organization schema, SSG-rendered pages and canonical URLs, the same patterns the scoring engine checks for.
What it proves
That the audit we sell is backed by an engine anyone can read, run locally, or point their own agent at — the scoring rules are not a black box behind a paywall. The extension and the paid audit intentionally run different rule counts for a stated reason (client-side privacy vs. server-side E-E-A-T checks that need crawling), and that distinction is documented rather than smoothed over.