Local models and AI providers
Granello does not have its own AI service. In Settings → AI models you choose the provider and the model, and you can use a different one for the AI notes and for the chat.
Two kinds of provider
Section titled “Two kinds of provider”| Provider type | Used for |
|---|---|
| Anthropic | Claude, the default provider |
| OpenAI-compatible | LM Studio (http://localhost:1234/v1), Ollama (http://localhost:11434/v1), OpenAI, OpenRouter and any server that exposes /chat/completions |
- The list of models is read from the server. Test checks that the provider answers.
- Each provider has its own API key in the Keychain. Local servers usually do not need one.
Keep everything on your Mac
Section titled “Keep everything on your Mac”Add a local provider (a server on localhost) and select it for both AI notes and Chat. From then on, no text leaves your Mac.
To make sure of it for one meeting whatever the settings say, set that meeting to hardened: it only ever uses a provider on localhost.
The context of local models
Section titled “The context of local models”An hour of meeting is tens of thousands of tokens. Local servers silently cut what does not fit, and some start with a small context. Enter it in the provider’s Context (tokens) field: Granello then estimates the size of each request and stops with a clear error, instead of writing notes from half a transcript.
The reasoning that some local models print before answering is removed from the notes.
Transcription is always local by default
Section titled “Transcription is always local by default”Speech is transcribed on your Mac by whisper.cpp, whatever AI provider you use. Sending audio to an online transcription service is a separate option, off by default: see how privacy works.
