Does Privatemode store my source code or prompts?

No. All processing happens inside hardware-isolated confidential computing environments. Your prompts and code context are encrypted before leaving your machine, decrypted only inside a hardware-isolated environment whose memory stays encrypted, and discarded after the response is generated. Prompts and responses are never stored or used for model training; only operational metadata such as token usage, timestamps, and request status is kept for billing and monitoring.

Can I use tab completions with Privatemode?

Not today. GitHub Copilot does not allow changing its tab completion model, and Continue, which did, was discontinued in June 2026. Chat, editing, and agent mode run on Privatemode; inline completions stay with whatever completion model you use.

Can I verify that the server is actually running inside confidential computing?

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 Visual Studio Code

VS Code gets its AI from extensions, and each one brings its own model connection. Privatemode sits behind Copilot Chat and Cline alike: instead of the cloud models they normally call, they run on open-weight models, so your code is encrypted before it leaves and stays encrypted in memory while it is processed.

Introduction

The challenge

Each extension sends your code to its own provider

Copilot Chat and Cline both read your code and send it to the model provider they are configured for. With conventional providers, that code is processed in plaintext on their servers, once per extension.

The solution

One proxy behind both

The Privatemode extension registers open-weight models inside Copilot's own model picker, so Copilot Chat runs on them instead of the GPT, Claude, Gemini, and other models Copilot offers, without leaving its interface. Cline reaches the same local proxy by base URL, and that proxy is what verifies the service and encrypts each request.

Benefits

Why use Privatemode AI with Visual Studio Code?

Native extension available

Also works with Cline

End-to-end confidentiality

Learn how

Free tier available

How to get started

How to set up Privatemode with VS Code

Get your API key

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

Set up VS Code

The cookbook in the Privatemode docs walks you through running the local proxy and installing the Privatemode extension for GitHub Copilot Chat, and optionally connecting Cline.

Cookbook

FAQ

Frequently asked questions about VS Code with Privatemode

Two extensions are officially supported: GitHub Copilot Chat for AI chat, editing, and agent mode, and Cline for agentic coding. The Privatemode VS Code extension handles the Copilot integration. Cline connects directly via the OpenAI-compatible API. Continue, which used to be the third option, was acquired by Cursor and discontinued in June 2026.