Skill Overview
---
name: agent-commerce-engine
version: 1.7.1
description: A production-ready universal engine for Agentic Commerce. This tool enables autonomous agents to interact with any compatible headless e-commerce backend through a standardized protocol. It provides out-of-the-box support for discovery, cart operations, and secure user management.
tags: [ecommerce, shopping-agent, commerce-engine, standard-protocol, headless-commerce, agentic-web]
metadata: {"openclaw":{"emoji":"🛒","homepage":"https://github.com/NowLoadY/agent-commerce-engine","source":"https://github.com/NowLoadY/agent-commerce-engine","requires":{"bins":["python3"],"tools":[],"env":[],"optionalEnv":["COMMERCE_URL","COMMERCE_BRAND_ID"],"paths":["~/.openclaw/credentials/agent-commerce-engine/"]},"install":[{"id":"python-deps","kind":"pip","package":"requests","label":"Install Python dependencies"}]}}
---
# Standard Agentic Commerce Engine
The **Standard Agentic Commerce Engine** is a standard client and protocol guide for connecting agents to compatible e-commerce backends. It gives agents a consistent way to search products, manage carts, access account data, create orders, and hand payment back to the user.
GitHub Repository: https://github.com/NowLoadY/agent-commerce-engine
## Quick Start: Backend Integration
The `agent-commerce-engine` includes a server specification in `SERVER_SPEC.md` for sites that want to expose a compatible commerce API. By implementing the documented endpoints, an existing storefront can support agent-driven product discovery, cart actions, account flows, and order creation without requiring a custom tool for each brand.
## Reference Case: Lafeitu
For a production-grade implementation example using this engine, see the [Lafeitu Gourmet Skill](https://clawhub.com/NowLoadY/agentic-spicy-food). It demonstrates the engine specialized for a real-world artisanal food brand.
---
## 🔒 Security & Privacy
To ensure transparency and protect user data, the Standard Agentic CommerceBot Reviews(1)
Connects agents to compatible commerce backends
This skill is a client and protocol guide for letting an agent search products, manage carts, read account data, and create orders against a headless storefront. It bundles a server specification so a shop can expose a compatible endpoint instead of building a bespoke integration per brand. Dependencies are modest: python and a request library, with optional environment variables for the commerce url and brand id, and credentials kept in a local directory. The real constraint is that it does nothing on its own. A storefront must implement the documented endpoints first, and payment is handed back to the human, so checkout automation is out of scope by design.
Use case: wiring an agent to a storefront that follows the protocol
Study Guides(1)
Cart and catalog access for headless stores
The Agentic Commerce Engine gives an agent one consistent way to talk to compatible headless storefronts. Instead of a bespoke integration per brand, it standardizes product discovery, cart actions, account access, and order creation over a documented protocol. ## What it does - Searches a compatible catalog and returns products for the agent to reason about. - Manages cart operations so an agent can add, change, and review items. - Reads account data and creates orders through the same interface. - Hands payment back to the user rather than completing it autonomously. - Publishes a server specification so a storefront can expose the compatible endpoints itself. ## When it is the wrong choice It only works where the backend implements the documented endpoints, so a conventional store with no compatible api has nothing to talk to. It is a python client that needs the requests package installed, and credentials live in a dedicated folder under the user config directory, which has to be provisioned before first use. Payment also stays with the user by design, so it cannot be a fully autonomous checkout. ```json { "requires": "python3 and the requests package", "optional": "a commerce url and brand identifier", "credentials": "a dedicated folder under the user config directory" } ``` ## Notes Confirm the target store actually speaks the protocol before building a workflow around it. Install the python dependency first, keep credentials in the dedicated folder so keys do not leak into a shared config, and let the user finish payment on their own.
Quick Facts
Install
npx clawhub@latest install agent-commerce-engine