Is my code encrypted before it leaves my machine?

Yes. The Privatemode proxy runs locally and encrypts all code context, prompts, and responses before they leave your machine. It also performs remote attestation to verify the integrity of the Privatemode service, ensuring end-to-end protection for every AI request Zed makes.

Does Privatemode store or learn from my code?

No. Privatemode is designed to never learn from your data. All inference requests are processed confidentially using confidential computing, and no code, prompts, or responses are retained after processing. This goes beyond policy promises — the confidential computing architecture, together with reproducible builds, makes data retention technically impossible.

Do I still need the Privatemode proxy with Zed?

Yes. The proxy is a lightweight local process that handles encryption and remote attestation. It verifies that the Privatemode service is running in a genuine confidential computing environment before sending any data. Zed connects to the proxy as if it were a standard OpenAI endpoint.

How does this compare to using Zed’s built-in AI providers?

Zed’s built-in providers (Anthropic, OpenAI, etc.) send your code context directly to those services. While Zed states they don’t train on your data, the providers still process your code in the clear. Privatemode adds a cryptographic guarantee: your code is encrypted end-to-end and processed inside a confidential computing enclave, so neither the AI provider nor Privatemode can see your data.

Integrating Privatemode AI with Zed

With Privatemode and Zed, you can use state-of-the-art cloud AI models confidentially, powering Zed’s Agent Panel, Inline Assistant, and Text Threads without exposing your code.

Introduction

Use cloud-based AI in Zed without compromising data privacy

Code with AI, keep your source code private

Zed users value performance and control. But using cloud AI features like the Agent Panel or Inline Assistant means sending code context to third-party providers. Privatemode removes that trade-off by providing an OpenAI-compatible, end-to-end encrypted service that never exposes your code to cloud or service providers.

No need for stripped-down forks

Privacy-conscious developers have turned to forks like Zedless that strip AI features entirely. With Privatemode, you keep Zed’s full AI capabilities (Agent Panel, Inline Assistant, Text Threads) while ensuring your code stays encrypted end-to-end.

Cloud-level AI — fully encrypted

Based on confidential computing, Privatemode gives Zed users access to state-of-the-art models while keeping all code context always encrypted, even during inference. Your prompts, code snippets, and AI responses are never visible to anyone.

Benefits

Why use Privatemode AI with Zed?

End-to-end encrypted AI coding

Integrating Privatemode into Zed brings cloud-AI capabilities to your editor while keeping your code confidential through end-to-end encryption and confidential computing. Your code context, prompts, and AI responses are encrypted before they leave your machine.

State-of-the-art model selection

With Privatemode, you can choose from state-of-the-art LLMs to power Zed’s Agent Panel, Inline Assistant, and Text Threads — all running confidentially.

Native integration, no plugins needed

Zed has built-in support for OpenAI-compatible endpoints. Just add Privatemode to your settings.json and all AI features work instantly — no extensions or workarounds required.

How to get started

How to set up Privatemode in Zed

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 Zed to use Privatemode

Open Zed and go to Settings (Cmd+,). Zed natively supports OpenAI-compatible endpoints, so add Privatemode as a custom provider in your settings.json under language_models > openai_compatible. Set the api_url to your Privatemode proxy’s /v1 endpoint.

Walk through our interactive demo

FAQ

Frequently asked questions about using Privatemode with Zed

All of them. Since Privatemode uses the OpenAI-compatible endpoint that Zed natively supports, the Agent Panel, Inline Assistant, and Text Threads all work out of the box. You configure Privatemode once in settings.json and every AI feature routes through it automatically.