CommerceTXT – An open standard for AI shopping context (like llms.txt)
Hi HN, author here. I built CommerceTXT because I got tired of the fragility of extracting pricing and inventory data from HTML. AI agents currently waste ~8k tokens just to parse a product page, only to hallucinate the price or miss the fact that it's "Out of Stock". CommerceTXT is a strict, read-only text protocol (CC0 Public Domain) designed to give agents deterministic ground truth. Think of it as `robots.txt` + `llms.txt` but structured specifically for transactions. Key technical decisions v1.0: 1. *Fractal Architecture:* Root -> Category -> Product files. Agents only fetch what they…
CommerceTXT – An open standard for AI shopping context (like llms.txt) launched on December 16, 2025 with 20 votes, #581 of 11,628 launches that month and more than 90% of that year's launches.
In plain words
CommerceTXT is an open standard text protocol designed to provide AI agents with reliable product, pricing, and inventory data from e-commerce sites. Rather than parsing HTML, agents access structured product information in a fractal file system, reducing token usage from roughly 8,500 to 380 per product while eliminating hallucination risks around prices and stock status. The read-only format follows the pattern of robots.txt and llms.txt, offering deterministic ground truth for AI-driven shopping interactions without transaction capabilities to avoid security issues.
written from the facts on this page · September 2026
From the sources
The CommerceTXT Protocol — transaction-ready context for AI agents. Like llms.txt, but for e-commerce.
TL;DR: llms.txt is for content discovery. CommerceTXT is for commerce transactions. If AI needs to know your price, inventory, or shipping policy—you need CommerceTXT. Real-time stock levels eliminate "Is it available?" hallucinations. Stock: 42 LowStockThreshold: 10 RestockDate: 2025-12-20 Impact: AI can say "Only 42 left" instead of guessing. Handle recurring payments for SaaS and subscription products. Plans: - Monthly: 29.99 - Annual: 299.00 Trial: 7 Days Free Impact: AI compares one-time vs. subscription pricing accurately. Aggregated review data in 50 tokens instead of scraping 15,000. Rating: 4.7 / 5.0 Count: 1243 TopTags: "Great battery" Impact: 99.7% token reduction for review…from commercetxt.org
In the maker’s words, at launch
Hi HN, author here. I built CommerceTXT because I got tired of the fragility of extracting pricing and inventory data from HTML. AI agents currently waste ~8k tokens just to parse a product page, only to hallucinate the price or miss the fact that it's "Out of Stock". CommerceTXT is a strict, read-only text protocol…
Does a similar job
all alternatives →
YourNextStore – an open-source Shopify with Stripe as the back end2024 · github.com · ▲285We’re building Your Next Store, a modern, ultra-fast, open-source commerce in Next.js with Stripe as the backend - no DB required. Selling online is often more complex than it needs to be. Setting up a storefront with great performance can feel daunting and time-consuming. There are many plugins, libraries, etc - the choice can be overwhelming. Plus, in e-commerce, the backend and frontend are often written in different languages (e.g., PHP, Python, or Ruby for the backend). This increases the complexity and makes code management more challenging, especially for teams. After working in…
30k IKEA items in flat textJan 2026 · huggingface.co · ▲55OP here. I took the unofficial IKEA US dataset (originally scraped by jeffreyszhou) and converted all 30,511 products into a flat, markdown-like protocol called CommerceTXT. The goal: See if a flatter structure is more efficient for LLM context windows. The results: - Size: 30k products across 632 categories. - Efficiency: The text version uses ~24% fewer tokens (3.6M saved total) compared to the equivalent minified JSON. - Structure: Files are organized in folders (e.g. /products/category/), which helps with testing hierarchical retrieval routers. The link goes to the dataset…
AgentReadyFeb 2026 · agentready.cloud · ▲118Compression API that reduces prompt size by 40-60% before sending to your LLM. Your API key never leaves your environment.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, December 2025
the whole month →- GP
Life & fun · Dec 2025 · dosaygo-studio.github.io
Hi everyone! My name's Luke and I made the original Jmail here alongside Riley Walz. We had a ton of friends collaborate on building out more of the app suite last night in lieue of DOJ's "Epstein files" release. Please AMA!
Life & fun · Dec 2025 · jmail.world
PlanEat AI▲733AI turns your health goals into a 7-day menu & grocery list
AI · Dec 2025 · planeatai.com
Community, All the HN belong to you. This is an archive of hacker news that fits in your browser. When I made HN Made of Primes I realized I could probably do this offline sqlite/wasm thing with the whole GBs of archive. The whole dataset. So I tried it, and this is it. Have Hacker News on your device. Go to this repo (https://github.com/DOSAYGO-STUDIO/HackerBook): you can download it. Big Query -> ETL -> npx serve docs - that's it. 20 years of HN arguments and beauty, can be yours forever. So they'll never die. Ever. It's the unkillable static archive of HN and it's…
Dev tools · Dec 2025 · hackerbook.dosaygo.com
