Redox AI Integration
Redox AI agents run through Bonfire Terminal, a local-first app that drives the Redox healthcare data integration API from AI on your own machine. Automate patient data exchange and interoperability workflows, commanded securely from Slack, Telegram, or Discord.
What Bonfire can do in Redox
Real actions from the Redox API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Search patients | Patient | POST /fhir/R4/{destination}/{environment}/Patient/_search |
| Get patient | Patient | GET /fhir/R4/{destination}/{environment}/Patient/{id} |
| Search encounters | Encounter | GET /fhir/R4/{destination}/{environment}/Encounter |
| Search observations | Observation | GET /fhir/R4/{destination}/{environment}/Observation |
| Search documents | DocumentReference | GET /fhir/R4/{destination}/{environment}/DocumentReference |
| Search coverage | Coverage | GET /fhir/R4/{destination}/{environment}/Coverage |
Redox 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
Redox — questions
Can Bonfire automate Redox?
Yes. Bonfire runs on your machine, holds your Redox credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Redox API to run the actions you ask for in chat.
Does my Redox 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.