In a hybrid AI setup, the work environment runs locally, but language processing can use an external provider. What exactly stays with you, and what goes outside? This article explains it component by component.
These components run on a system at your location: the Hermes environment itself, with its configuration, settings, and skills; your projects and files (code, documents, and knowledge base); session history with earlier decisions and context; and access permissions, including who can use it and with which rights. Repositories can live where you choose, such as GitHub or an internal Git server.
Language processing, handled by the model that interprets your prompts and generates answers, can use an external provider such as OpenAI or Anthropic. You decide which model to use and which data may be sent to it.
If you use an external provider, Hermes sends the context needed for the specific task. It does not send everything: the intended scope is what the task needs, within the data boundaries you set.
| Aspect | Local | Cloud |
|---|---|---|
Hermes environment | Configuration, settings, skills | Not required |
Projects and files | Code, documents, knowledge base | Only what the task needs |
Session history | Earlier decisions and context | Not stored as the local session archive; sent context follows provider policies |
Access permissions | Who has access and with which permissions | Not applicable |
Language processing | Local model (if the hardware supports it) | External provider (OpenAI, Anthropic) |
You stay in control in three ways. You choose the provider, or a local model if your hardware justifies it. You decide which data may go to the provider, per project or task. And you set up your own provider account, so Voltti has no access to your usage.
Read more about local AI for businesses or about security and privacy. Compare local and cloud AI in our article on local AI vs. cloud AI.
No. Only the context needed for a specific task goes to the provider. You decide which data that may include.
Yes, with a local language model. That requires powerful hardware, such as a GPU, and quality may be lower than with an external model. We advise you on this during the intake.
You do. Voltti advises you, but you set up your own model provider account. You have full control over your usage.
