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.

How does encryption affect response speed?

The Privatemode proxy adds only milliseconds for encryption, decryption, and remote attestation. Response times are comparable to standard cloud AI APIs. You can also enable prompt caching with the --sharedPromptCache flag on the proxy to speed up repeated context windows.

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.

Does OpenCode work the same way through Privatemode?

OpenCode's full feature set is supported through Privatemode. Since Privatemode provides an OpenAI-compatible API, OpenCode communicates with it using the standard @ai-sdk/openai-compatible provider. The only difference is that your data is encrypted end-to-end.

Use Confidential AI with OpenCode

OpenCode is an open-source AI coding agent for the terminal. With Privatemode, every prompt and code snippet is protected end-to-end through confidential computing, even while being processed by AI.

Introduction

Coding with AI without exposing your code

Introduction

AI-assisted coding shouldn't mean exposing your code

OpenCode running in a terminal with Privatemode as the AI provider

The challenge

Your codebase leaves with every prompt

OpenCode reads across your project to generate and edit code, and sends that context to a cloud LLM. With a conventional provider, your source, architecture decisions, and business logic are processed in plaintext on the provider's servers.

The solution

A provider that cannot read your code

The Privatemode proxy runs locally. It verifies the integrity of the Privatemode cloud service through remote attestation, and encrypts every request before it leaves your machine. Cloud-side, your data is protected end-to-end by confidential computing and stays encrypted in memory even during processing. By design, neither the infrastructure provider nor we can read it.

Benefits

Why use Privatemode AI with OpenCode?

End-to-end confidentiality

Learn how

Cloud-grade AI models

See models

Free tier available

Set up OpenCode to use Privatemode

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

Read the docs

FAQ

Frequently asked questions about OpenCode with Privatemode

Privatemode offers a range of models running inside confidential computing environments with full encryption. See the model overview.