An assistant that reads your messages is only as private as the place it runs. OpenClaw is local-first: a gateway on your own server with agents that receive and answer messages across WhatsApp, Telegram, Slack and Discord, keeping the conversation data on your VPS.
What you get
- One assistant across channels: WhatsApp, Telegram, Slack, Discord and more
- Local-first gateway, so conversations stay on your server
- Modest requirements: around 1 GB of memory and 3 GB of disk
- Offshore, no KYC, crypto billing, with an optional Tor address
Get it running
Pick a small VPS
Around 1 GB of memory is enough for the gateway itself, since the heavy model work happens through whichever AI backend you connect. Any entry offshore VPS will do.
Install it in one click
Install OpenClaw from the catalog with a hostname for the gateway interface. The certificate is issued automatically. See how one-click installs work.
Store the gateway token
The install generates a gateway token that every API call must present. Copy it into your password manager: on a public hostname, that token is what stands between the internet and your assistant.
Sign in and connect your channels
Log in through the interface, then connect only the messaging channels you actually want the assistant to handle.
The install can optionally take session cookies copied from a logged-in browser to skip first-run onboarding. Those cookies are bearer credentials for that account: anyone who reads them, from the config, a log or a backup, can act as you. Prefer logging in through the interface. If you do use them, treat them as a password, keep them out of repositories and backups, and expect them to expire.
Connected to a messaging account, it can read conversations and send messages under your name. Connect the minimum set of channels, review what the agents are allowed to do, and keep in mind that anyone who compromises the gateway inherits that reach.
The point of running this yourself is that your message history and contacts never become a third party’s dataset. Combine it with a self-hosted model and the conversation never leaves your infrastructure at all.
There is rarely a reason for the gateway interface to be reachable by the whole internet. Restrict access, or publish it as a Tor onion service instead of a public hostname. See how to publish a Tor .onion site.
Start now
Spin up an offshore VPS and install OpenClaw from the catalog, or read the documentation.