CLI commands
cnry runs --tail --format jsonOpen Source · Run It Yourself
Your tools for AI search
Track what ChatGPT, Claude, Gemini, and Perplexity say about your business alongside search and server data. Give your agent tools to make approved fixes.
Latest release v7.65.0. Your data, API keys, and server. Stored in SQLite.
Install CanonryNode 22+
brew tap canonry/canonrybrew install canonryThen run cnry init and cnry serve.
Your agent · Your computer
Use the AI agent you already have.
Connect with the command line, REST, MCP, webhooks, or a Codex or Claude Code plugin. AUQ, a SaaS SEO and AEO agency, reviewed these tools.
Choose the native plugin or standalone MCP. Do not use both at once. Plugin guide
Connect your agentNative plugin
codex plugin marketplace add Canonry/canonrycodex plugin add canonry@canonryFirst run cnry init --skip-skills --skip-mcp, then cnry start.
One Shared System
One set of data. Four ways to use it.
Shared project dataCanonry
REST endpoints
GET /api/v1/citationsMCP tools
tools/competitor_gapWebhook events
citation.gainedCompare Your Results
One timeline. Three sources.
Match dates and URLs to look for patterns. These do not prove cause and effect. Server logs can show bot visits and clicks from AI that a browser tracking tag misses. The full walkthrough follows the steps from your first check to a client report.
AI answersNames · Links
Google SearchTimes shown · Clicks · Click rate
Server eventsBots · User visits · Clicks from AI
Compare byDate + URL
- 01
Search interest
Times shown · Clicks · Click rate
- 02
Server activity
Bots · User visits · Clicks from AI
How Work Flows
Check the facts. Approve the work.
- 01
Connect your data
- 02
Check the starting point
- 03
Agent plans the work
- 04
You approve
What You Can Do
Check. Act. Run. Connect.
Observe
- Links in AI answersGemini · ChatGPT · Claude · Perplexity · Muse · local LLMs
- Server trafficCloudflare · Cloud Run · Vercel · WordPress
- Search resultsGSCGA4Bing
- Local AEOQuestions · results · hotel and booking gaps
- Common Crawl backlinksMonthly link data · timed updates · DuckDB
Act
- WordPress changesContent fixes
- JSON-LD schemaStructured data
- Send pages to search toolsGoogle · Bing · IndexNow
Operate
- Many clientsYAML · cnry apply
- Timed data updatesAI search · visits · Business Profile
- Alerts when results dropWebhooks
- Client reportscnry report <project>
Connect
- Your own agentCLI · REST · webhooks
- MCP adapterAny agent that uses MCP
- Native pluginsCodex · Claude Code
- AeroBuilt in · starts after each run
Two-Minute Tour
See how it runs on your computer.
Watch on YouTubeClear answers
Common questions about Canonry.
What is Canonry?
Canonry tracks AI mentions and citations alongside search data, site traffic, and technical audits. Run it on your own server and use the web app, CLI, REST API, MCP tools, or webhooks. The source code is public.
Does Canonry replace my agent?
No. Canonry gives your agent evidence, tools, spending limits, and approval checks through CLI, REST, MCP, webhooks, or a Codex or Claude Code plugin. Aero is the bundled agent.
Where does Canonry store my data?
You host Canonry for your own team. By default, project data lives in one SQLite file on your computer or server. You control API keys, backups, and where it runs.
Which AI tools can it track?
Canonry supports Gemini, OpenAI, Claude, Perplexity, Meta's Muse Spark, and local models with OpenAI-compatible APIs. Optional browser checks capture supported AI apps when their answers differ from API results.
How does my agent connect?
Codex and Claude Code can install the Canonry plugin. Other agents can use CLI commands with JSON output, a versioned REST API, or MCP tools loaded as needed. Signed webhooks can trigger work in other systems.
Is the source public?
Yes. Read the code, issues, design, and guides on GitHub. The npm package is @canonry/canonry. Canonry 5.0 and later use the MIT license.
Open Source · Runs on Your Server
Track your AI visibility.
Install Canonry to check, fix, and track your own site.