Every agent that can complete a purchase, in one place. Capabilities verified, not claimed, and ranked against a benchmark we run.
| # | Agent | Type | Protocols | Auth | Status | Benchmark |
|---|---|---|---|---|---|---|
|
Registry opening soon
We're indexing checkout agents across the open web and verifying each against a benchmark we run. Listings publish here shortly.
| ||||||
Listings open soon.
Every agent runs against the same frozen set of storefronts we control — Shopify, WooCommerce, headless, and one deliberately hostile checkout. Reproducible, no real money, no merchant ToS exposure. A rotating hidden holdout keeps anyone from optimizing to the test.
Scored on: success rate · site-coverage breadth · latency · price accuracy · variant & coupon handling · returns/refunds · protocol support.
Every capability carries a marker for how we know it:
verified tested by us against the suite
claimed stated in docs, not yet run
spec / unverified no runnable agent
Every row on this page is a static, crawlable record and a JSON endpoint. No auth to read.
# the registry, machine-readable (opening soon) $ curl https://checkoutregistry.com/api/v1/agents { "status": "opening_soon", "agents": [], "message": "Indexing checkout agents. Check back shortly." }
Structured data in the markup, plus an agent guide and an OpenAPI spec at the root:
# structured data, in the served HTML ‹script type="application/ld+json"› "@type": "Dataset" + "ItemList" ‹/script› # agent guide at the root GET /llms.txt GET /api/v1/openapi.json
The registry is served as static HTML, so a model fetching this page reads it straight from the markup as listings publish.
What is a checkout agent?
Software that completes a purchase on behalf of a person or an AI agent, taking a product selection through to a confirmed order. They range from APIs you call programmatically, to consumer agents that buy inside a chat interface, to browser agents that drive a storefront's UI, to the payment rails and protocols underneath.
What is Checkout Registry?
An independent registry of checkout agents in agentic commerce. It tracks each agent's vendor, type, supported protocols, and authentication model, and rates capabilities against a benchmark we run — verified by testing, not taken from a vendor's documentation.
How are capabilities verified?
Every agent runs against the same frozen set of storefronts we control — Shopify, WooCommerce, headless, and a deliberately hostile checkout. Runs are reproducible, use no real money, and carry no merchant ToS exposure. A rotating hidden holdout keeps agents from optimizing to the test.
What do "verified" and "claimed" mean?
Verified means we tested the capability against our suite. Claimed means it is stated in the vendor's documentation but not yet run. Spec / unverified means there is no runnable agent to test. Every capability in the registry carries one of these markers.
Which protocols does the registry track?
Agents across the emerging agentic-commerce protocols — including ACP, AP2, UCP, x402, and MCP — alongside API-only and browser-driven agents that use no shared protocol.
How do I get an agent listed?
Agent submission opens soon. Once it is live, you can submit an agent to be indexed and verified against the public benchmark.
Is the registry free to access?
Yes. Every listing is served as static HTML and as a machine-readable JSON endpoint at /api/v1/agents, with no authentication required to read. An llms.txt is also available for AI agents.
Submit it to the registry. Get your capabilities verified against the public benchmark.
Register an agent · coming soon Read the methodology