Stripe AI Integration
Stripe AI agents run on your own machine with Bonfire Terminal, driving your payments platform through the Stripe API to issue refunds, chase failed charges, and reconcile payouts. Local-first control, no cloud middleman, triggered straight from Slack or Telegram.
What Bonfire can do in Stripe
Real actions from the Stripe API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Get Account | account | GET /v1/account |
| Post Account Links | account_links | POST /v1/account_links |
| Get Accounts | accounts | GET /v1/accounts |
| Post Accounts | accounts | POST /v1/accounts |
| Get Apple Pay Domains | apple_pay | GET /v1/apple_pay/domains |
| Post Apple Pay Domains | apple_pay | POST /v1/apple_pay/domains |
| Get Application Fees | application_fees | GET /v1/application_fees |
| Get Application Fees Fee Refunds Id | application_fees | GET /v1/application_fees/{fee}/refunds/{id} |
Stripe 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
Stripe — questions
Can Bonfire automate Stripe?
Yes. Bonfire runs on your machine, holds your Stripe credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Stripe API to run the actions you ask for in chat.
Does my Stripe 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.