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, ensuring end-to-end protection for every request.

Does Privatemode store or retain data from Jan sessions?

No. Privatemode is designed to never learn from your data. All inference requests are processed confidentially 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 (OpenAI, Mistral, etc.) process your prompts on their servers in plaintext. Privatemode uses confidential computing so your data is encrypted even during inference. Neither the AI provider nor Privatemode can see your conversations.

Integrating Privatemode AI with Jan

Jan runs AI locally for offline, private conversations. Privatemode extends Jan with frontier cloud models while keeping the same privacy guarantee through end-to-end encryption and confidential computing.

Introduction

Use cloud AI in Jan without compromising your privacy

screenshot of privatemode setup in jan ai

Offline-first Setup, now with cloud power

Jan is designed for users who want full control over their AI conversations. But local models are limited by your hardware. Privatemode lets you access frontier cloud models while maintaining the privacy-first approach Jan users value.

Your conversations stay encrypted

Every message is encrypted end-to-end before leaving your machine. The Privatemode proxy handles encryption and remote attestation locally, so the AI provider never sees your conversations in plaintext. Privatemode never stores or learns from your data.

Native remote model support

Jan has built-in support for custom OpenAI-compatible remote endpoints via the 'Any OpenAI Compatible API' option. Add Privatemode in the model settings and your chat interface works instantly with encrypted cloud models, no extensions needed.

Benefits

Why use Privatemode AI with Jan?

End-to-end encrypted AI conversations

Integrating Privatemode into Jan brings cloud-AI capabilities to your desktop chat while keeping your conversations confidential. Every prompt and response is encrypted through end-to-end encryption and confidential computing. Privatemode never learns from your data.

Access frontier models beyond local limits

Local models are constrained by your device's memory and GPU. With Privatemode, Jan users can access state-of-the-art LLMs that far exceed what local hardware can run, while keeping the same privacy guarantees.

Built-in remote model support

Jan natively supports connecting to OpenAI-compatible remote endpoints. Add Privatemode in the model settings and all chat features work instantly. Your local models stay available for offline use alongside Privatemode.

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.

docker run -p 8080:8080 ghcr.io/edgelesssys/privatemode/privatemode-proxy:latest --apiKey <your-api-key>

Run the Privatemode proxy

The proxy verifies the integrity of the Privatemode service using confidential computing-based 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 natively supports custom OpenAI-compatible endpoints via the 'Any OpenAI Compatible API' remote model option. You add Privatemode as a remote provider, set the endpoint URL and model name, and the chat interface works as usual with encrypted cloud models.