Is my assistant's context encrypted before leaving my machine?

Yes. The Privatemode proxy runs locally and encrypts all data before it leaves your machine. It also performs remote attestation to verify the integrity of the Privatemode service, ensuring end-to-end confidentiality for every request OpenClaw makes.

Does Privatemode store or retain data from my conversations?

No. Privatemode is designed to never learn from your data. All inference requests are processed confidentially using confidential computing, and no prompts, memory entries, or responses are retained after processing.

Do all OpenClaw features work with Privatemode?

Any OpenClaw feature that uses the configured agent model, including chat, browser automation, and skills, will route through Privatemode. Features that depend on a specific provider's proprietary API may need that provider configured separately.

How does encrypted inference affect performance?

Response times are comparable to standard cloud AI services while providing full data protection.

Integrating Privatemode AI with OpenClaw

OpenClaw is an open-source personal AI assistant that can be controlled via your messaging apps and runs locally on your machine. With Privatemode as its AI inference service, every AI request and response stays end-to-end encrypted, keeping your assistant's context fully confidential.

Introduction

Use cloud AI in OpenClaw without exposing your assistant's context

screenshot of openclaw chatbot in telegram

Personal assistants need powerful models

OpenClaw runs a conversational agent across messaging apps with persistent memory, browser automation, and shell access. Frontier LLMs make the assistant feel competent, but standard cloud providers have access to every prompt in plain text. For an assistant wired into your personal life and workflows, that is a hard limit.

Encrypted inference

Privatemode exposes an OpenAI-compatible endpoint that OpenClaw connects to as a custom provider. Every AI interaction is encrypted end-to-end. The AI service or cloud provider never sees your assistant's context in plaintext.

Hardware-enforced, not only policy

Based on confidential computing, Privatemode processes your data inside a hardware-enforced enclave. This is verifiable through remote attestation and open-source code, going beyond standard cloud providers' privacy policies.

Benefits

Why use Privatemode AI with OpenClaw?

End-to-end encrypted personal assistant

Pointing OpenClaw at Privatemode brings cloud-AI capabilities to your personal assistant while keeping AI interaction confidential. Encryption is enforced by confidential computing and Privatemode never trains on your data.

State-of-the-art model selection

With Privatemode you can pick from current open-weight models to power OpenClaw's chat and agentic features.

Native support

OpenClaw supports custom OpenAI-compatible providers. Add Privatemode with a base url pointing to your local proxy and the assistant routes every request through encrypted inference. No plugins needed.

How to get started

How to set up Privatemode in OpenClaw

Using Privatemode as your inference provider keeps all OpenClaw AI interactions confidential by design. You still have to take care of reducing the blast radius of your agent's actions. Privatemode does not manage agent permissions or action scope. You should carefully read OpenClaw's security and sandboxing guidelines.

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 OpenClaw

Install OpenClaw following the instructions from the official website.

Configure OpenClaw

This terminal session shows a minimal example configuration to help you get started with OpenClaw. We use Telegram here for its simple setup. Adjust the configuration to fit your needs.