Is my source code encrypted before it leaves my machine?

Yes. The Privatemode proxy runs locally and encrypts all code context 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 code from Tabby sessions?

No. Privatemode never learns from your data. All requests are processed using confidential computing, and no code, prompts, or responses are retained after processing.

Which Tabby features work with Privatemode?

Chat runs on Privatemode through the openai/chat connector, and repository indexing plus the Answer Engine run on the openai/embedding connector with Qwen3-Embedding-4B. Inline completion stays local: Tabby's completion needs a fill-in-the-middle model with a matching prompt template, and Privatemode's models are chat models without that training.

How does encrypted processing affect performance?

Privatemode uses confidential computing hardware to minimize overhead. Confidential computing adds a small overhead. Response times are comparable to conventional AI services, and your data stays encrypted in memory during processing.

Integrating Privatemode AI with Tabby

Tabby is a self-hosted coding assistant with completion, chat, and an answer engine over your indexed repositories. Privatemode supplies the chat and embedding models it needs, with your code encrypted in memory even during processing.

Introduction

A screenshot of the tabby ML user interface

The challenge

Self-hosted, and capped by what you can host

Teams run Tabby on their own infrastructure to keep their code in-house. That choice caps them at the models their hardware can serve, which are often smaller than the best available, and switching to a conventional cloud backend would send their code to the provider in plaintext.

The solution

Chat and embeddings from one proxy

Tabby needs a chat model and an embedding model, and the Privatemode proxy serves both, so repository indexing and the answer engine are protected in the same way as chat. Requests are encrypted before they leave your infrastructure and processed in a hardware-isolated environment whose memory stays encrypted.

Benefits

Why use Privatemode AI with Tabby?

Chat and repository search

See models

End-to-end confidentiality

Learn how

Free tier available

How to get started

How to set up Privatemode with Tabby

Get your API key

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

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.

Install Tabby

To install Tabby on macOS using Homebrew, run the command below. This will download and set up the Tabby CLI so you can run and manage the Tabby server.

Create the following configuration file for Tabby

Create the configuration directory and then generate the config file that points both of Tabby's remote model roles, chat and embedding, at the Privatemode proxy.

Start Tabby

To start Tabby with the configuration you just created, run the following command launching the Tabby server.

Done

You've successfully set up Tabby with Privatemode.

FAQ

Frequently asked questions about using Privatemode with Tabby

Minimal changes. Tabby natively supports OpenAI-compatible HTTP model backends. You add a few lines to your config.toml pointing the chat and embedding models to the Privatemode proxy, and every request is encrypted on your machine before it leaves.