Luma AI assistant
Luma AI assistant support comes from Bonfire Terminal running on your own computer. A private assistant powered by Claude, GPT, or offline Llama uses your Luma event context to speed event planning, keeping guest information local and fully under your control.
What Bonfire can do in Luma
Real actions from the Luma API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Create event | Events | POST /v1/events/create |
| Get event | Events | GET /v1/events/get |
| Update event | Events | POST /v1/events/update |
| Add guests | Guests | POST /v1/events/guests/add |
| List guests | Guests | GET /v1/events/guests/list |
| Update guest status | Guests | POST /v1/events/guests/update-status |
| List calendar events | Calendar | GET /v1/calendars/events/list |
| Get self | User | GET /v1/users/get-self |
Luma 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
Luma — questions
Can Bonfire automate Luma?
Yes. Bonfire runs on your machine, holds your Luma credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Luma API to run the actions you ask for in chat.
Does my Luma 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.