{
  "id": 17296200,
  "title": "Four open-source tools for AI in e-commerce, and what building them taught me",
  "url": "https://urgent.news/2026/10/30/four-open-source-tools-for-ai-in-e-commerce-and-what-building-them",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-30T22:01:31.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/sadrmanesh/four-open-source-tools-for-ai-in-e-commerce-and-what-building-them-taught-me-5abl"
  },
  "original_language": "en",
  "account": "Naser Sadrmanesh, an AI product engineer and founder, has created four open-source tools for e-commerce AI. These tools are small, MIT licensed, and each was built because a real project needed them. llm-search-eval helps determine if a new search method is better by comparing nDCG scores and using a label pool with both human and LLM judgments. The Model Context Protocol (MCP) allows AI agents to interact with stores safely, with tools for catalog search, orders, refunds, coupons, and more. commerce-agent-skills provides a library of 29 skills for coding agents in e-commerce, covering payment gateways, returns, inventory, accessibility, and more. Lastly, persian-rag is a retrieval system designed to work with Persian language nuances, such as different code points and spelling variations. All four tools share common habits, including documentation, continuous integration, and automatic publishing to various package managers. They are open to contributions and feedback.",
  "summary": "I'm Naser Sadrmanesh, an AI product engineer and founder working on online stores. Over the last months I turned the tools I kept rebuilding for clients into four open-source projects. They are small, MIT licensed, and each one exists because a real project needed it. This post explains what each does and the design decision behind it. 1. llm-search-eval: is the new search actually better? Every…",
  "key_points": [
    "Four open-source tools created for AI in e-commerce",
    "llm-search-eval compares search methods using nDCG scores",
    "Model Context Protocol enables safe AI agent interactions"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}