Ships as a GitHub container

AI customer support for ecommerce stores
grounded in your orders, reviews and policies

Quenvyra helps ecommerce merchants answer order, product review and policy questions with AI grounded in their store data. Support Shopify, WooCommerce, BigCommerce and Adobe Commerce with a self-hosted app.

Choose an AI support plan for your store

Start with a free trial, run a self-hosted SQLite setup, or scale with MariaDB vector store.

  • $2
    • Full-featured Light edition
    • SQLite system of record
    • Embedded ChromaDB vector store
    • Admin console and storefront demo
    • Auto-expires after 14 days
    • Perfect for evaluating Quenvyra
  • $42
    one-time
    • Perpetual single-shop license
    • SQLite system of record
    • Embedded ChromaDB vector store
    • Admin console and storefront demo
    • Runs with a single docker command
    • Mock fallbacks without an API key
  • Custom
    • Multi-shop MariaDB license
    • MariaDB vector store for advanced similarity search
    • Multi-tenant architecture
    • Enterprise analytics dashboard
    • Admin console and storefront demo
    • Dedicated support available
Trial Edition

Start using Quenvyra for 14 days with full access to all features of the Light edition. Perfect for evaluating whether Quenvyra is the right fit for your store. Your trial will automatically expire after 14 days. Full-featured evaluation license for $2. Includes admin console and storefront demo Vite pages.

Each license is valid for one Shopify shop. All editions include the same AI features.

AI customer support for orders, reviews and store policies

Give your team grounded answers without switching between order records, review apps and policy documents.

Order & customer lookup

Exact match by email or order number, plus natural-language search across orders, tickets and policies.

Product review intelligence

Aggregate reviews into answers: sizing trends, recurring defects and what customers actually say.

Multi-agent RAG

Specialised agents for orders, reviews and knowledge cooperate to ground every answer in your store data.

Answers, not record lists

LLM synthesis turns retrieved context into a direct reply your support agents can send or edit.

Tenant-isolated

Every row and vector carries the shop domain, and every query filters on it.

Built for Headless Commerce

Seamlessly connects to WooCommerce, Shopify Hydrogen, BigCommerce, Remix or Next.js React storefronts using lightweight APIs and real-time webhooks and plugins.

Ticket inbox with suggested replies

One click drafts a reply grounded in the order, past tickets and your policies. Agents review and send.

Knowledge base manager

Add, edit and delete policies, FAQs and product docs. Articles are chunked and re-embedded automatically.

Guardrail tester

Probe how the agent handles refund, off-topic and risky requests before customers see it.

Customer widget & admin console

A customizable React + TypeScript front end is bundled in the same container: an embeddable shopper widget (order lookup, ask a question, submit ticket) and a team admin console.

Manage customer support in one console

Review tickets, manage store knowledge and configure how AI answers customer questions.

TicketsKnowledge BaseDashboardPreferencesGuardrail Test
#4 Want a refund for earbuds
dave@example.com · order 1001
Resolved
#3 Earbuds keep disconnecting from phone
carol@example.com
Open
#1 Watch stopped charging after a week
alice@example.com · order 1003
Open

A customer support widget for your storefront

Help shoppers look up orders, ask product questions and submit support requests. Add the customizable widget to Shopify Hydrogen, WooCommerce, BigCommerce or a React storefront.

Order LookupAsk a QuestionSubmit Ticket
Order lookup
Email
Order number
Look up
// app/routes/support.tsx (Hydrogen)
import { QuenvyraWidget } from '@quenvyra/widget'
import '@quenvyra/widget/style.css'

export default function Support() {
  return (
    <QuenvyraWidget
      apiUrl="https://your-host:8000"
      shopDomain="your-shop.myshopify.com"
      tabs={['order', 'ask', 'ticket']}
      theme={{ primary: '#19c6a5', radius: 12 }}
    />
  )
}
  • TypeScript React component built with Vite, shipped as an npm package and a script bundle
  • Themeable: colors, radius, fonts and copy are all props
  • Order lookup, natural-language questions and ticket submission
  • Talks to the Quenvyra backend you host in Light or Enterprise mode

How it works

Webhooks and knowledge in, grounded answers out.

Shopify webhooks ──▶ API ──▶ SQL store (orders, customers, tickets, reviews)
                                │
Knowledge articles ──▶ chunk ───┤
(policies, FAQs, docs)          ├─▶ Vector store (orders · tickets · knowledge)
                                │
Agent query ──▶ /search/ask ────┴─▶ similarity search ──▶ LLM synthesis ──▶ Answer
Structured

Exact lookups by order number or email.

Semantic

Natural-language search across all sources.

Optional LLM

Works with mock fallbacks until you add an API key.

Quickstart

Pull the image from GitHub Container Registry and run.

Light
docker run -p 8000:8000 -v ./data:/app/data \
  -e OPENAI_API_KEY=sk-... \
  ghcr.io/quenvyra/support-rag:latest
Enterprise (MariaDB)
docker run -p 8000:8000 \
  -e DATABASE_URL=postgresql://user:pass@db:5432/quenvyra \
  -e OPENAI_API_KEY=sk-... \
  ghcr.io/quenvyra/support-rag:latest

API on localhost:8000, interactive docs at /docs, admin console at /admin, customer widget at /client.

Embed the widget in your Headless storefront
<script src="https://your-host/widget.js" defer></script>
<quenvyra-widget shop="your-shop.myshopify.com"></quenvyra-widget>

Tuned for your catalog

Bike shops

Deterministic fitment data decides compatibility; the agent explains why a part fits in plain language.

Clothing shops

Fit feedback from reviews and returns becomes sizing guidance and proactive chat on hesitation.

Other shops

Custom electronics and other niche products can be managed with tailored guidance and proactive support.

Ready to try Quenvyra?

Tell us about your store and we will help you pick the right edition.