LightBox AI Integration
LightBox AI agents from Bonfire Terminal support your real estate data workflows using your LightBox context and credentials. They help gather property intel, organize parcels, and prep reports, running local-first on your own machine so research stays on-device.
What Bonfire can do in LightBox
Real actions from the LightBox API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Search address | Geocoding | GET /v1/addresses/search |
| Autocomplete address | Geocoding | GET /v1/addresses/_autocomplete |
| Reverse geocode | Geocoding | GET /v1/addresses/reverse |
| Get parcels by address | Parcels | GET /v1/parcels/address |
| Get parcel by ID | Parcels | GET /v1/parcels/{countryCode}/{id} |
| Get parcel by APN | Parcels | GET /v1/parcels/us/fips/{fips}/apn/{apn} |
| Get structures by address | Structures | GET /v1/structures/address |
| Get structures on parcel | Structures | GET /v1/structures/_on/parcel/{countryCode}/{id} |
LightBox 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
LightBox — questions
Can Bonfire automate LightBox?
Yes. Bonfire runs on your machine, holds your LightBox credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the LightBox API to run the actions you ask for in chat.
Does my LightBox 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.