Is data encrypted before leaving my machine?

Yes. The Privatemode proxy runs locally and encrypts all data before it leaves your machine. It also performs remote attestation to verify the integrity of the Privatemode service, so every request is protected end to end by confidential computing.

Does Privatemode store or retain data from Jan sessions?

No. Privatemode never learns from your data. All requests are processed using confidential computing, and no prompts or responses are retained after processing.

Can I still use local models alongside Privatemode?

Yes. Jan lets you switch between local and remote models freely. You can use Privatemode for tasks that benefit from frontier cloud models and local models for quick, offline work.

How does this differ from Jan's other remote providers?

Jan's standard remote providers process your prompts on their servers in plaintext. Privatemode uses confidential computing so your data stays encrypted in memory throughout processing. By design, neither the infrastructure provider nor Privatemode can read your conversations.

Integrating Privatemode AI with Jan

Jan runs models locally and connects tools through MCP. Privatemode adds a remote model strong enough to run those tools reliably, with every request encrypted before it leaves your machine and encrypted in memory while it is processed.

Introduction

screenshot of privatemode setup in jan ai

The challenge

MCP tools need a bigger model than a laptop runs

Jan connects tools through MCP, and Jan's own docs note that many open-source models are not built for tool calling or handle it poorly, so the connectors work best with a larger model than most laptops can run. The usual way out is a conventional cloud provider, which processes your conversations in plaintext on its servers.

The solution

A remote model that handles the tools

Jan adds Privatemode alongside its local models, and the models behind it handle tool calling and structured outputs, so MCP tools work reliably. The proxy on your machine verifies the service through remote attestation and encrypts each request before it leaves.

Benefits

Why use Privatemode AI with Jan?

Reliable tool calling for MCP

See models

End-to-end confidentiality

Learn how

Free tier available

How to get started

How to set up Privatemode in Jan

Get your API key

If you don't have a Privatemode API key yet, you can generate one for free here.

Run the Privatemode proxy

The proxy verifies the integrity of the Privatemode service using remote attestation. The proxy also encrypts all data before sending and decrypts data it receives.

Configure Jan to use Privatemode

FAQ

Frequently asked questions about using Privatemode with Jan

Minimal changes. Jan supports custom OpenAI-compatible endpoints under Settings > Model Providers > Add Provider, with the OpenAI-compatible API format. You add Privatemode there with the base URL http://localhost:8080/v1 and any placeholder API key, add the model ID (Jan also tries to detect the models from the proxy), and the chat interface works as usual.