Which models are available for each extension?

GitHub Copilot Chat works with gpt-oss and Qwen3-Coder through the Privatemode extension. Continue uses qwen3-coder-30b-a3b for fast tab completions. Cline connects with gpt-oss-120b for agentic coding tasks. All models 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.

Can I use tab completions with Privatemode?

Yes. GitHub Copilot does not allow changing its tab completion model, so for privacy-preserving inline completions, use the Continue extension configured with Qwen3-Coder. The Privatemode extension guides you through disabling Copilot's built-in tab completions to avoid conflicts.

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 Visual Studio Code

VS Code supports AI-assisted coding through GitHub Copilot, Continue, and Cline. With Privatemode, every prompt and code snippet is encrypted end-to-end through confidential computing, keeping your codebase fully confidential.

Introduction

VS Code integration

Benefits

Why use VS Code with Privatemode

Introduction

Use VS Code AI extensions without exposing your source code

screenshot of the visualstudio code editor

AI coding extensions send your code to cloud providers

VS Code's AI ecosystem includes GitHub Copilot Chat for AI chat and editing, Continue for tab completions, and Cline for agentic coding. Each extension sends your code context to a cloud LLM provider. 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. Point your VS Code extensions at 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 Visual Studio Code?

End-to-end encrypted coding sessions

Every prompt you type and every file your AI extension 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.

Works with three popular AI extensions

Privatemode integrates with GitHub Copilot Chat for AI-powered chat, editing, and agent mode. Use Continue for privacy-preserving tab completions with Qwen3-Coder. Or connect Cline for agentic coding workflows with gpt-oss-120b. Mix and match extensions based on your workflow.

Install the Privatemode extension and go

Install the Privatemode VS Code extension to connect GitHub Copilot to Privatemode. For Continue and Cline, simply point the base URL to localhost:8080.

See the guide

Set up VS Code to use Privatemode

Follow the step-by-step guide in the documentation to configure VS Code extensions with Privatemode as your inference provider.