Getting Started

Your PrivateClaw instance is a Confidential VM, a machine whose memory is hardware-encrypted by the CPU itself. Not even the cloud provider can read what's running inside. This guide walks you through verifying that, testing your setup, and connecting a messaging provider.

1. Verify Your TEE

The first thing to do after SSH-ing into your CVM is verify that it's actually running in a Trusted Execution Environment:

privateclaw verify

This runs five checks:

• SEV-SNP Hardware. Requests a fresh SEV-SNP attestation report from the AMD CPU and verifies the VCEK certificate chain back to the AMD root CA. Proves the VM is running on genuine SEV-SNP silicon with memory encryption active.
• TPM Attestation. Reads the HCL (Hardware Compatibility Layer) report from the virtual TPM, which binds the SEV-SNP measurement to the boot state.
• Host Key Binding. Confirms the SSH host key hash recorded inside the attestation report matches the live host key, proving you are connected to the same machine that produced the attestation.
• Inference Provider. Verifies that OpenClaw is configured to send prompts through the Confidential AI private inference endpoint and that endpoint returns a valid attestation header proving it also runs in a TEE.
• External Access Lockout. Confirms only your SSH key is authorized and the firewall blocks lateral network access. No one else can get in.

You can run privateclaw verify at any time: after updates, after reboots, whenever you want reassurance. The checks are read-only and instant.

Why this matters

Most cloud VMs trust the cloud provider implicitly. The hypervisor can read your memory, the host OS can inspect your disk, and operators can access your data through management tools. Confidential computing changes that. With AMD SEV-SNP, the CPU encrypts your VM's memory with keys that the hypervisor never sees. privateclaw verify lets you independently confirm these guarantees are active. You don't have to take anyone's word for it.

2. Test Your Setup

Once you've verified the TEE, check that OpenClaw is working:

openclaw tui

This launches the terminal UI. Try sending a message to confirm inference is working end-to-end through the private pipeline. Press q to quit.

3. Connect a Messaging Provider

This is the most important step. OpenClaw is designed to work through messaging apps like WhatsApp and Signal, so you can use your AI assistant without being SSH'd into the CVM.

openclaw configure --section channels

This walks you through connecting one or more messaging providers. Once connected, you can chat with your OpenClaw instance from your phone or desktop. All messages route through the CVM and private inference pipeline, so the same privacy guarantees apply.

Help & Troubleshooting

SSH Keys

PrivateClaw uses SSH keys as your identity. No passwords, no accounts, no email required. Most machines do not have an SSH key pair by default.

Step 1: Check if you already have an SSH key

ls ~/.ssh/id_ed25519.pub

If you see "No such file or directory", you need to create one (Step 2). If you see a path, skip to Step 3.

Step 2: Create an SSH key

ssh-keygen -t ed25519 -f ~/.ssh/id_ed25519 -N '' -q

This creates a key pair with no passphrase. The private key stays on your machine; the public key identifies you to PrivateClaw.

Step 3: Connect to PrivateClaw

ssh privateclaw.dev

This opens the management TUI where you can choose your plan and provision your Confidential VM.

Connection Errors

Permission denied (publickey)

Your SSH key is not being sent. Common causes:

• You don't have an SSH key. Create one with the command in Step 2 above.
• Your key is in a non-default location. Use ssh -i /path/to/key privateclaw.dev.
• Your SSH agent isn't running. Run ssh-add to add your key.

WARNING: REMOTE HOST IDENTIFICATION HAS CHANGED

This means the server's host key changed since you last connected. If PrivateClaw has announced maintenance or infrastructure changes, this is expected. To fix:

ssh-keygen -R privateclaw.dev

Then reconnect with ssh privateclaw.dev. If you weren't expecting this, contact support before reconnecting.

Connection refused or Connection timed out

• Check your internet connection.
• If the service is under maintenance, try again in a few minutes.
• Make sure you're connecting to privateclaw.dev (not a different hostname).

Egress (Network Bandwidth)

What counts toward egress?

Egress measures outbound internet traffic from your CVM. This includes anything your CVM sends to the public internet: downloading packages, pulling container images, sending data to external APIs, or browsing the web from within your VM.

What does NOT count?

• Private inference traffic between your CVM and the Confidential AI endpoint travels over the VNet (private network) and is not counted.
• SSH sessions to your CVM are inbound traffic, not egress.
• Internal orchestrator communication (callbacks, health checks) stays within the VNet.

How is egress tracked?

All outbound internet traffic from CVMs goes through a dedicated NAT Gateway. We measure exactly the bytes that traverse it, which aligns with what Azure charges for outbound data transfer. VNet-internal traffic bypasses the NAT Gateway entirely and is free.

What happens when I hit my limit?

• Free tier: Outbound internet is blocked until your billing period resets (30 days). SSH access and private inference continue to work. You can upgrade to a paid plan to unblock immediately.
• Paid tiers (Basic, Pro): You are never blocked. Traffic beyond your included allowance is billed as overage at $0.087/GB (Azure pass-through cost). Overage charges appear on your next invoice.

How can I reduce egress?

• Use the private inference endpoint (already configured by default) instead of external AI APIs.
• Avoid large downloads inside the CVM when possible.
• Monitor your usage in the management TUI (ssh privateclaw.dev).

What's Next

• Explore OpenClaw's features: OpenClaw documentation
• Run privateclaw verify anytime to re-check your TEE
• Learn more about our privacy model: About PrivateClaw

Need help?

If you run into any issues or have questions, reach out at support@privateclaw.dev.