Shopify AI Integration
Shopify AI agents run from Bonfire Terminal on your own Windows or Mac, driving your storefront directly through the Shopify API. They update products, fulfill orders, and adjust inventory on command, keeping merchant data local instead of routed through a cloud SaaS.
What Bonfire can do in Shopify
Real actions from the Shopify API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List products | Products | GET /admin/api/2025-01/products.json |
| Create product | Products | POST /admin/api/2025-01/products.json |
| Update product | Products | PUT /admin/api/2025-01/products/{product_id}.json |
| List orders | Orders | GET /admin/api/2025-01/orders.json |
| Create customer | Customers | POST /admin/api/2025-01/customers.json |
| Set inventory level | Inventory | POST /admin/api/2025-01/inventory_levels/set.json |
| Create fulfillment | Fulfillments | POST /admin/api/2025-01/fulfillments.json |
| Create draft order | Draft Orders | POST /admin/api/2025-01/draft_orders.json |
Shopify agents in action
On your machine, not a SaaS
Bonfire Terminal
- Your keys & data stay on your device
- Perpetual license — no per-seat SaaS fee
- Any connected model — Claude, GPT, Gemini or Grok
- Offline Llama for local, private reasoning
- Driven from chat you already use
Cloud AI middleman
- Keys & data pass through a third-party server
- Recurring subscription, usage caps
- Model locked to the vendor
- Yet another dashboard to log into
Shopify — questions
Can Bonfire automate Shopify?
Yes. Bonfire runs on your machine, holds your Shopify credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Shopify API to run the actions you ask for in chat.
Does my Shopify data go to the cloud?
Bonfire runs on your desktop and keeps your keys local — it isn't a SaaS holding your data. Only the specific request you approve is sent to your chosen AI model.
Which AI models can I use?
Any connected model — Claude, GPT, Gemini or Grok. A fully offline Llama model runs locally for private reasoning but can't reach live APIs.