Which models are available?

The AI Assistant plugin fetches available models directly from the Privatemode proxy when you click Test Connection. Currently, gpt-oss and Qwen-Coder are available. Use gpt-oss for core AI features and Qwen-Coder for fast inline completions. Both run inside confidential computing environments with full encryption.

Does Privatemode store my source code or prompts?

No. All inference happens inside hardware-isolated confidential computing environments. Your prompts and code context are encrypted before leaving your machine, decrypted only inside the secure enclave for processing, and discarded after the response is generated. Nothing is stored or used for model training.

What does Offline mode do?

Enabling Offline mode in the AI Assistant settings prevents data from being sent to any external service other than the configured provider. Since your provider is the local Privatemode proxy, this ensures all AI traffic stays within the encrypted Privatemode channel.

Can I verify that the server is actually running in a secure enclave?

Yes. The Privatemode proxy performs remote attestation before every session, verifying the server's integrity against known cryptographic hashes. The proxy and server code are open source with reproducible builds, so you can audit exactly what runs on the server side.

Using Confidential AI with JetBrains IDEs

JetBrains IDEs support AI coding through the AI Assistant plugin. With Privatemode AI, every prompt and code snippet is encrypted end-to-end through confidential computing, keeping your codebase fully confidential.

Introduction

JetBrains integration

Benefits

Why use JetBrains with Privatemode

Introduction

Use JetBrains AI Assistant without exposing your source code

AI-powered IDEs send your code to cloud providers

JetBrains AI Assistant brings AI chat, code generation, and inline completions to IntelliJ IDEA, PyCharm, CLion, and other JetBrains IDEs. By default, all prompts and code context are sent to external cloud providers. For teams working on proprietary software, regulated applications, or sensitive IP, that means source code leaves your control.

Privatemode keeps your code confidential

Privatemode provides an OpenAI-compatible API backed by state-of-the-art models running inside confidential computing environments. Configure the JetBrains AI Assistant to use the Privatemode proxy and your source code, prompts, and AI responses are encrypted end-to-end. Not even Privatemode can see your data.

Hardware-enforced, not just policy

The Privatemode proxy runs locally on your machine and encrypts all data before it leaves. On the server side, inference runs inside hardware-isolated confidential computing environments (AMD SEV / Intel TDX). The proxy verifies server integrity through remote attestation before every session. Your code is never stored and never used for model training.

Benefits

Why use Privatemode AI with JetBrains IDEs?

End-to-end encrypted coding sessions

Every prompt you type and every file the AI Assistant reads is encrypted by the local Privatemode proxy before leaving your machine. Responses are decrypted only on your device. The models run inside confidential computing environments protected by AMD SEV and Intel TDX hardware. Your source code, architecture decisions, and business logic remain confidential throughout the entire session.

Full AI Assistant capabilities

The JetBrains AI Assistant plugin works with Privatemode for AI chat, code generation, and inline completions. The plugin fetches available models directly from the Privatemode proxy.

Easy setup

Setting up your JetBrains IDE to use Privatemode only requires a few minutes of your time.

See the guide

Set up JetBrains AI Assistant to use Privatemode

Follow the step-by-step guide in the documentation to configure JetBrains AI Assistant with Privatemode as your inference provider.