> For the complete documentation index, see [llms.txt](https://invinos.gitbook.io/invinos/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://invinos.gitbook.io/invinos/core-app-modules/local-llm.md).

# Local LLM

Artificial intelligence is one of the most powerful tools available to users — but it comes with major privacy trade-offs when used via cloud APIs. Every prompt submitted, question asked, or reply received is often stored, analyzed, or reused by the service provider.

Invinos eliminates this surveillance by embedding local language models that run fully offline. These models do not connect to external servers, do not require internet access, and do not log user activity. Users can generate text, translate content, summarize documents, or ask questions in complete privacy.

Each model runs inside a sandbox, and no prompt is saved after inference. When the app closes, all AI session data is wiped. This allows for powerful natural language reasoning — without putting user thoughts, ideas, or patterns into external hands.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://invinos.gitbook.io/invinos/core-app-modules/local-llm.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.