Revit AI Integration
Revit AI agents work through Bonfire Terminal, the local-first desktop app that keeps AI on your machine. Using your Revit project context, agents help you plan BIM models, document design decisions, and organize deliverables, all controllable from Slack, Telegram, or Discord.
What Bonfire can do in Revit
Real actions from the Revit API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List engines | Design Automation | GET /da/us-east/v3/engines |
| Create appbundle | Design Automation | POST /da/us-east/v3/appbundles |
| Create activity | Design Automation | POST /da/us-east/v3/activities |
| Submit workitem | Design Automation | POST /da/us-east/v3/workitems |
| Get workitem status | Design Automation | GET /da/us-east/v3/workitems/:id |
| Start translation job | Model Derivative | POST /modelderivative/v2/designdata/job |
| Fetch manifest | Model Derivative | GET /modelderivative/v2/designdata/{urn}/manifest |
| List hubs | Data Management | GET /project/v1/hubs |
Revit 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
Revit — questions
Can Bonfire automate Revit?
Yes. Bonfire runs on your machine, holds your Revit credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Revit API to run the actions you ask for in chat.
Does my Revit 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.