Confidential AI coding agents

Plug a confidential Kimi Latest into Claude Codeto protect your IP.

Quickstart

Get started in one prompt

Paste one prompt into Claude Code and it sets itself up on Privatemode, guided by the official docs and reversible at any time.

Claude Code logo

Claude Code

Anthropic's agentic CLI for your codebase. Pick a mode: try Privatemode in a single project first, or make every session confidential right away.

Try pasting this into Claude Code. It sets up this project only.

Set up Privatemode as the confidential inference backend for Claude Code - in this project only, so I can test it and cleanly undo it.
  1. 1. Get your API key from the dashboard
  2. 2. Paste the prompt into Claude Code
  3. 3. Test it: say "undo" to revert everything

No risk: Only local project settings are modified and a local proxy is created. Your overall setup stays untouched.

Security and privacy first

Don't rely on agreements. Rely on modern technology.

End-to-end encrypted, even during processing

Your prompts and code are encrypted on your device and processed inside a hardware-isolated environment whose memory stays encrypted the whole time. Neither Privatemode nor any cloud provider can read them. Not by policy, but by architecture.

Hardware-enforced isolation

Inference runs inside confidential computing environments (AMD SEV, Intel TDX, Nvidia Confidential Computing). Remote attestation verifies the server before every session.

Never stored, never trained on

Your code is processed in memory only. Nothing is stored, nothing is used for training. The stack is open source with reproducible builds.

Fits into how your team already works.

Pi

Run the open-source, bring-your-own-model coding agent from your terminal. Privatemode adds frontier-scale models while keeping every prompt and response fully private.

Read guide
Pi coding agent logo

GitLab Duo

Back GitLab Duo Self-Hosted with Privatemode and serve code suggestions, chat, and agentic flows from a model you control. Prompts and source code stay end-to-end encrypted.

Read guide
GitLab logo

Claude Code

Use Claude Code as an autonomous coding agent without sending your full codebase to Anthropic's infrastructure. Privatemode provides a compatible API so all code and context stays private.

Read guide
claude code logo

JetBrains

Use JetBrains AI Assistant across IntelliJ, PyCharm, GoLand, and more. Cloud-grade completions and chat, with no code or context leaving your control.

Read guide
JetBrains logo

OpenCode

Run the open-source AI coding agent from your terminal. Privatemode keeps every prompt and file it reads fully private, with no data stored or used for training.

Read guide
OpenCode logo

Visual Studio Code

Use GitHub Copilot, Continue, or Cline in VS Code with private cloud AI. Point any extension to Privatemode and your code stays fully private.

Read guide
Visual Studio Code logo

Tabby

Connect your self-hosted Tabby instance to frontier cloud models for stronger code completion. Keep the privacy of local inference while moving to cloud-scale AI.

Read guide
the logo of Tabby ML

Xcode

Power Xcode's Swift Assist and code generation with Privatemode as the AI backend. No extensions required, and your Swift code is never stored or shared.

Read guide
xcode logo

Need custom integration?

Would you like to use Privatemode as the AI provider in a specific tool that we do not yet support?

Let us know!

n8n logo white
Xcode logo
jan ai logo