The most comprehensive open-source technical AEO (Answer Engine Optimization) audit tool. Scores any website across 16 ranking factors that decide whether AI answer engines (ChatGPT, Perplexity, Gemini, Claude) will cite your content.
- Grade any URL across 16 AEO factors: structured data,
llms.txt, E-E-A-T, extractability, snippet eligibility, and more. Scoring - Audit a whole site from its sitemap; per-page findings roll up into ranked fixes. Sitemap mode
- Audit built HTML offline in CI: a
next export/dist/outdirectory, no network. Static output - Detect the platform / CMS / framework: WordPress, Webflow, Shopify, Next.js, Vercel. Platform detection
- Opt in to Lighthouse, geographic, and agent-skill factors. Optional factors
text,json,markdown, andagentoutput with CI-friendly exit codes. CLI reference- Agent-native output: a versioned
schemaVersion, a slim--format agentdecision, ranked structured fixes, and stable finding codes so integrations key on codes, not prose. API - Use as a library (API) or from Claude Code via the
/aeoskill (skill).
Website: canonry.ai
npx @ainyc/aeo-audit https://example.comPrints a graded report. Common variations:
# Every page in the sitemap, site-wide issues only
npx @ainyc/aeo-audit https://example.com --sitemap --top-issues
# JSON for CI/CD (exit 1 when score < 70)
npx @ainyc/aeo-audit https://example.com --format json
# A built directory, offline
npx @ainyc/aeo-audit ./out --base-url https://example.comFull flag and mode reference: docs/cli.md.
The package ships a Claude Code / ClawHub skill. Install it, then:
/aeo audit https://example.com
Modes: audit, fix, schema, llms.txt, monitor. See the skill guide.
| Doc | What's in it |
|---|---|
| CLI reference | Every flag, mode, and exit code |
| Scoring | The 16 factors, weights, grading scale |
| Programmatic API | runAeoAudit, runSitemapAudit, runStaticAudit |
| Skill | /aeo modes and install |
| Changelog | Release history |
| Roadmap | What's planned |
git clone https://github.com/Canonry/aeo-audit.git && cd aeo-audit
pnpm install && pnpm run typecheck && pnpm run build && pnpm test && pnpm lintSee CONTRIBUTING.md.