📡Hermes & OpenClaw: your in-house agents
What if your mini-PC became an assistant you drive from your phone? Hermes and OpenClaw turn the machine into a self-hosted agent, reachable by chat, backed by your local models.
Until now, you drive your agent from a terminal, sitting in front of the machine (or over SSH). But once you have an always-on mini-PC, another idea becomes possible: what if you could send it a message from your phone, out in the street, and it got to work? That’s exactly what a family of self-hosted agent tools makes possible. The two most interesting to know: OpenClaw and Hermes.
The common idea: a bridge between a chat and an agent
OpenClaw and Hermes start from the same principle. You install a gateway (a small service) on the mini-PC. This gateway links a chat channel : typically Telegram : to an agent running on the machine, backed by your local models via Ollama and/or Claude in the cloud.
The result: you write to a bot the way you’d write to a colleague. “Summarize the latest news for me”, “kick off the deployment”, “find where authentication is handled in my repo”. The message arrives on the mini-PC, the agent acts (it has tools, remember the agent loop), and replies. Your workshop in your pocket, with nothing unplugged.
OpenClaw
OpenClaw is an open-source agent gateway you host yourself. It connects a chat channel to a local agent, rich in native commands, and extensible via plugins: you can teach it to administer your machine, orchestrate several models, trigger your own scripts. It’s the ideal tool to build yourself a tailor-made personal assistant.
Hermes
Hermes (from the Nous Research lab) pursues the same idea with its own approach: a command-line / TUI agent interface, paired with a gateway that gives you remote access to your coding agent (driving Claude Code from Telegram, for example) and a small web dashboard. It too relies on local models via Ollama, and overlaps largely with OpenClaw, to the point where you can migrate from one to the other. If what you mainly want is to reach your dev agent from the outside, it’s a very direct entry point.
Why the mini-PC is what makes this great
These tools shine precisely because the machine is dedicated and always on:
- Always reachable. Your assistant never sleeps: the mini-PC stays awake while your laptop is closed.
- Private and frugal. Backed by a local model, it can run dozens of times a day with no marginal cost and no data leaving, exactly the hybrid logic: local for volume, Claude for the tough spots.
- Accessible from anywhere. Via your Tailscale private network and a channel like Telegram, you drive it from the other side of the world, securely.
Getting started, carefully
Install one gateway, just one to begin with
Choose OpenClaw or Hermes (they overlap, no need for both at the start). Follow the project’s official docs to install it on the mini-PC, and Vincent’s write-up for OpenClaw.
Connect your chat channel
Create a Telegram bot and connect it to the gateway. That’s what gives you the remote control from your phone.
Point it at your models
Configure the agent to use your local Ollama model for the everyday, and Claude for the hard tasks.
Lock down access, non-negotiable
Set up an allowlist: only you (your Telegram account) can talk to the bot. Without it, anyone who finds the bot could command your machine.
Run it as a service
Install the gateway as a systemd service so it restarts on its own (same logic as for the site or your scheduled agents).