Wave AI chatbot
Wave AI chatbot capability comes from Bonfire Terminal, letting you message a local-first assistant connected to Wave via API. Ask about outstanding invoices, cash flow, or expense totals from Telegram or WhatsApp, no cloud accounting middleman required.
How Bonfire works with Wave
Wave does not expose a public REST API we can drive directly. Instead Bonfire stores your Wave credentials and context locally on your machine and surfaces them to your chosen AI model, so an agent can reason over your Accounting Software data and draft, summarize, and prepare work — while your data stays on your own hardware.
Wave 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
Wave — questions
Can Bonfire automate Wave?
Yes. Bonfire runs on your machine, holds your Wave credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Wave API to run the actions you ask for in chat.
Does my Wave 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.