HomePod AI skills
HomePod AI skills come alive through Bonfire Terminal, where on-device AI orchestrates your smart speaker. Trigger music, scenes, and announcements with natural language while every instruction stays on your machine instead of a third-party cloud you cannot see or control.
What Bonfire can do in HomePod
Real actions from the HomePod API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Age Rating Declarations update instance | AgeRatingDeclarations | PATCH /v1/ageRatingDeclarations/{id} |
| App Categories get collection | AppCategories | GET /v1/appCategories |
| App Categories get instance | AppCategories | GET /v1/appCategories/{id} |
| App Encryption Declarations get collection | AppEncryptionDeclarations | GET /v1/appEncryptionDeclarations |
| App Encryption Declarations get instance | AppEncryptionDeclarations | GET /v1/appEncryptionDeclarations/{id} |
| App Info Localizations create instance | AppInfoLocalizations | POST /v1/appInfoLocalizations |
| App Info Localizations delete instance | AppInfoLocalizations | DELETE /v1/appInfoLocalizations/{id} |
| App Infos get instance | AppInfos | GET /v1/appInfos/{id} |
HomePod 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
HomePod — questions
Can Bonfire automate HomePod?
Yes. Bonfire runs on your machine, holds your HomePod credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the HomePod API to run the actions you ask for in chat.
Does my HomePod 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.