HubSpot AI features
HubSpot AI features gain new depth with Bonfire Terminal running locally on your own hardware. Using a connected model like Claude, GPT, or Gemini, it reads and writes your CRM through HubSpot's API, automating contact management and reporting, while offline Llama handles private on-device reasoning without any cloud SaaS.
What Bonfire can do in HubSpot
Real actions from the HubSpot API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List contacts | Contacts | GET /crm/v3/objects/contacts |
| Create contact | Contacts | POST /crm/v3/objects/contacts |
| Update contact | Contacts | PATCH /crm/v3/objects/contacts/{contactId} |
| Search contacts | Contacts | POST /crm/v3/objects/contacts/search |
| Create company | Companies | POST /crm/v3/objects/companies |
| Create deal | Deals | POST /crm/v3/objects/deals |
| Create ticket | Tickets | POST /crm/v3/objects/tickets |
| Associate records | Associations | PUT /crm/v4/objects/{objectType}/{objectId}/associations/{toObjectType}/{toObjectId} |
HubSpot 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
HubSpot — questions
Can Bonfire automate HubSpot?
Yes. Bonfire runs on your machine, holds your HubSpot credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the HubSpot API to run the actions you ask for in chat.
Does my HubSpot 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.