
Plug a confidential GLM Latest into
Claude Codeto protect your IP.
Paste one prompt into Claude Code and it sets itself up on Privatemode, guided by the official docs and reversible at any time.
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.
No risk: Only local project settings are modified and a local proxy is created. Your overall setup stays untouched.
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.
Inference runs inside confidential computing environments (AMD SEV, Intel TDX, Nvidia Confidential Computing). Remote attestation verifies the server before every session.
Your code is processed in memory only. Nothing is stored, nothing is used for training. The stack is open source with reproducible builds.
Run Pi on models larger than your own GPU, with your prompts kept confidential.
Duo Self-Hosted without running GPUs of your own.
Agentic coding across your whole repo, without the provider reading it.
Confidential coding in OpenCode: select Privatemode as the provider.
GitHub Copilot Chat and Cline on confidential open-weight models.
Chat and code search for self-hosted Tabby on a confidential model.

Xcode Intelligence on a confidential model instead of ChatGPT.
Would you like to use Privatemode as the AI provider in a specific tool that we do not yet support?
Let us know!
