In stock · 2–5 working days

Your AI agent,on hardware you own.

Always on, in your room. Bring the Claude, GPT or Gemini key you already pay for — no subscription to us, and not a cent on top of your tokens.

  • 30 days to send it back
  • No subscription, ever
  • Free delivery included
  • Ships from Bulgaria

Compatibility

It already speaks to all of this.

No logo wall here — a row of enterprise badges nobody can check is the fastest way to lose a reader who tries. What is true instead: the account you already pay for, the weights you already run and the tools already on your machine all point at it on the first evening.

  • Anthropic
  • OpenAI
  • Gemini
  • OpenRouter
  • Meta Llama
  • Mistral
  • DeepSeek
  • Qwen
  • Ollama
  • Hugging Face
  • NVIDIA
  • Telegram
  • Raycast
  • Obsidian
  • Cursor
  • n8n
  • LangChain
4cloud providers
One key each, billed to you by them. We never see a token of it.
8local models
Weights already on the drive, running on the box with no key at all.
6ways in
Telegram, your editor, your automations — or anything that speaks HTTP.

Why a box

You don’t need another AI subscription. You need somewhere to run the ones you have.

The models are already good. The keys are already in your password manager. What is missing is a machine that stays awake and does something with them.

01

It stops when you close the lid

The assistant you pay for lives in a tab. Shut the laptop and the research job dies, the inbox goes untriaged, the scheduled thing never runs. You are paying for a capability that is only awake when you are.

02

You are already paying twice

A Claude plan. A GPT plan. Then a third invoice from a service that resells you the same tokens at a markup, in its own credits, on its own servers — for the privilege of running them while you sleep.

03

Some things you just won't send

Contracts, patient notes, unreleased code. So you rewrite the real question into a vague one, get a vague answer back, and quietly do that half by hand instead.

Bring your own key

The key you already pay for.

Paste in the provider you are already billed by. The box talks to Anthropic or OpenAI exactly the way your laptop does — we run no proxy, take no cut and never see a token.

Anthropic

Claude

Your API key or Claude plan. Billed by Anthropic, not us.

OpenAI

GPT

Drop in the key you already use for everything else.

Google

Gemini

Long-context work, on the account you already have.

OpenRouter

300+ models

One key, the whole catalogue, switchable per task.

Ollama

Local

Runs on the box itself. No key, no bill, nothing leaves.

When nothing can leave

Pull the cable out. It still answers.

There is a model living on the drive, running on the box’s own silicon. No key, no invoice, no packet off your network — so the contract, the patient note and the unreleased repo can finally be the actual question instead of a vaguer one you rewrote to feel safe.

You choose, per task

A job arrives

Stays here

The model on the box

No key, no bill, nothing off the network.

Goes out

The key you already hold

Billed by Anthropic or OpenAI, exactly as now.

Already on the drive

  • Llama 3.1 8B
  • Qwen 2.5 7B
  • Mistral 7B
  • DeepSeek-R1 Distill 8B
  • Gemma 2 9B
  • Phi-4 Mini
  • Whisper
  • Nomic Embed

What it can hold

14 tok/s

A 8B-class model at 4-bit, fully resident in 8 GB of shared memory. It is not a frontier model and we will not pretend otherwise — it is the one that answers when the answer is not allowed to leave the room.

How you reach it

hermes.local

An OpenAI-compatible endpoint on your own network. Point your editor, your shortcuts or a six-line script at it and the only thing that changes is the base URL.

Not only chat

Speech and search

Whisper transcribes and Nomic embeds, both on the box. The recording of the call and the folder you searched never become anyone else's problem.

A HermesBox on a desk at dusk, beside a closed laptop

While you sleep

Awake at 3am, with your laptop shut.

Because it isn’t your laptop. Long jobs finish overnight, the inbox is triaged before you open it, and it messages you when something needs you — not the other way round.

The 90-Second Setup

Three steps. Then it is just there.

No Docker compose file, no CUDA versions, no quantisation rabbit hole. The hard part is already done and soldered down.

Plug it in

Power and Ethernet. It boots, finds itself on your network, and answers to hermes.local. No account to create, no setup wizard, no waiting list.

Paste in the keys you already have

Anthropic, OpenAI, Google, OpenRouter — whichever you're already paying for. The box uses your key and your plan; your provider bills you exactly what they billed you yesterday. We never see a token.

Message it from Telegram

Or the web UI, or the OpenAI-compatible endpoint your existing tools already speak. It's awake at 3am with your laptop shut, because it isn't your laptop.

What people point it at

Boring work, done overnight.

None of this is a demo. It is the middle of the week, handled by something that does not need you awake for it.

  • Email

    triage, drafts, follow-ups that actually go out

  • Browser

    fills forms, pulls data, clicks through the boring bit

  • Research

    long jobs that run while the laptop is shut

  • Reminders

    it messages you, not the other way round

  • Dev work

    reviews, refactors, scripted chores on a schedule

  • Not this

    training models, video work, or anything that needs more than 8 GB at once

In a real room

Somebody’s desk, on a Tuesday.

A HermesBox owner at their desk, one hand resting on the box

An owner’s desk. One cable, about 20 W, and a machine that is still working after you have walked away from it.

Agent Skills

652 things it already knows how to do.

Open, published skills — reading spreadsheets, filling PDFs, driving a browser, writing decks. One line each, and it goes and gets them itself.

hermes.local

$ hermes skills add pdf

installed · ready in this conversation

  • pdf
  • xlsx
  • docx
  • pptx
  • mcp-builder
  • webapp-testing
  • brand-guidelines
  • frontend-design
  • artifacts-builder
  • canvas-design
  • internal-comms
  • skill-creator
  • + 640 more
One line each
No config file to hand-write, no restart. Ask for it in Telegram and the box goes and gets it.
Plain folders of Markdown
Read a skill before you install it and edit it after. Nothing is compiled, encrypted or phoning home.
Your own count too
Drop a folder of your own instructions in and it behaves exactly like the other 652.
A HermesBox photographed on a studio grey

Built, not rendered

Twenty watts, one moving part.

A fan, and we will say so
Single managed fan, not silent. It is quiet in a room with anything else happening in it, and audible in a silent one. If you want it on a bedside table, this is the sentence to read twice.
Assembled and burnt in
Every unit is built, loaded and left running before it is boxed. The drive already has the weights on it, so the first boot is a first boot, not an install.
Nothing to hear from us again
No telemetry to switch off, because there is none. The box has no reason to report on you and it doesn't.

Specifications

A fifth of a lightbulb.

It draws about twenty watts and sits there doing your work while the laptop is shut.

Compute
67 TOPS

NVIDIA Jetson Orin Nano Super

Memory
8 GB

LPDDR5, shared with the GPU

Storage
512 GB

NVMe SSD

Draw
20 W

15–20 W typical — a fifth of a lightbulb

Model class
8B

4-bit quantised, fully resident

Throughput
14 tok/s

7B at Q4_K_M, single stream

Runtime
Ollama

plus llama.cpp and an OpenAI-style API

Cooling
Active

single managed fan, not silent

The trade

The same models. A very different arrangement.

Hosted agent
HermesBox
What it costs you
Another monthly fee
€549 once
Your API keys
Held on their servers
On a box in your room
Token billing
Resold to you, with a cut
Straight from your provider
When your laptop sleeps
Depends on their uptime
Still running, 20 W
Work you can't upload
Goes up anyway, or not at all
Stays on the local model
If the terms change
You migrate, on their schedule
You already own the machine

Compared against a hosted agent service, not against the model providers themselves — you keep those. HermesBox is where they run, not a replacement for them.

The HermesBox Promise

Four things we hold to, so you don't have to gamble.

Buying hardware from a company you had not heard of this morning is a leap. These are the terms that make it a small one.

Thirty days to send it back

Plug it in, connect your keys, push it hard for a month. If it isn't what you wanted, it goes back and we refund it. One email, no form, no restocking fee.

Not a cent on top of your tokens

Your key, your provider, your invoice. We take no cut, add no markup and run no proxy — the box talks to Anthropic or OpenAI exactly the way your laptop already does.

No subscription required

The hardware is a one-time purchase and it works fully without paying us anything again. There's no tier that unlocks the thing you just bought.

No telemetry, ever

There is no analytics to switch off, because there is none to begin with. The box has no reason to report on you and it doesn't.

Questions

The things people actually ask.

No, and it doesn't have to be. The box runs 7–8B models locally, which handle the everyday middle of the work — summarising, extraction, classification, drafting, first-pass code. For anything harder you point it at Claude, GPT or Gemini on your own key and get exactly the frontier model you're already paying for. The local side isn't the ceiling, it's the option for documents you'd never upload.

No, and you can't. You connect your own Anthropic, OpenAI, Google or OpenRouter key and the box calls those providers directly. They bill you at their rates, on the account you already have. We take no cut, add no markup and run no proxy in between — the €549 is the entire commercial relationship.

That's the intended way to run it. Paste in the keys you already have and the box uses your existing plans — nothing is duplicated and nothing new starts billing. If you'd rather not use a cloud provider at all, the local models on the box work with no key and no bill.

Because the dev kit isn't the product. That figure is a US list price before VAT, shipping and import — landed in Europe it is already meaningfully more — and what arrives is a bare board with an empty M.2 slot. Getting from there to this adds the 512 GB NVMe drive, the case, the active cooling, the assembly and the burn-in test, and the work of having the agent, the runtimes and the local weights already talking to each other on first boot. The price then includes EU VAT, delivery, thirty days to send it back for a full refund, and the 2-year legal guarantee of conformity. There is a margin on top of that — we build these, support them and answer the email — and a breakdown engineered to land on exactly €549 would be an insult to anyone able to do the sum in the first place. If it still doesn't look worth it, the thirty days are there so you can find out with our money rather than our argument.

Don't, yet. Trust the terms instead: use it for thirty days and send it back if it isn't right. And note what you are not being asked to trust us with — your API keys stay on hardware in your room, your tokens are billed by your provider, and there's no subscription that can be raised on you later.

No. It arrives with Ollama and llama.cpp installed, weights already on the drive, and a web UI at hermes.local. If you do want to go deeper — pulling different models, adjusting context, exposing it over Tailscale — that's all there, just not in your way.

Yes. It exposes an OpenAI-compatible endpoint on your local network, so anything that lets you set a base URL works: Cursor, Continue, Zed, Raycast, Obsidian plugins, n8n, LangChain, LlamaIndex, or a five-line Python script. Day to day, most people just message it on Telegram.

On the box, on your network. They are not synced to us, not held in a hosted dashboard, and not readable by anyone who hasn't got the machine. That's the practical difference between this and an agent service you sign into: revoking our access means unplugging a cable.

They cost nothing — they aren't ours to sell. A skill is a small folder of Markdown that teaches an agent one job properly: filling a PDF, cleaning a spreadsheet, reviewing a diff, writing to a brand guide. The box installs any of the 652 in the open Agent Skills ecosystem in a single line, and you can read one before installing it and edit it after. Your own folder of instructions works exactly the same way. Skills run against whichever provider you pointed the box at, so the one that reads a contract can stay on the local model while the rest go to Claude or GPT on your key.

Yes — anything Ollama or llama.cpp will run that fits in 8 GB, which in practice means GGUF up to about 9B at four-bit. The models it ships with are a starting point, not a walled garden. Pull your own with one command.

No. It has a single managed fan and it is quiet, but a page that told you a computer with active cooling makes no noise would be lying to you about the first thing you'd notice.

It ships from Bulgaria to the EU, UK, Switzerland and Norway. Shipping and EU VAT are included in the price shown — the number at checkout is the number you pay.

Send it back within thirty days of it arriving and we refund it in full. One email — no form, no restocking fee, no explanation required.

Still unsure? Ask us directly — a person answers.

The offer

One box, one price, and then it is yours.

HermesBox
In stockOne-time purchase

HermesBox

Assembled, loaded and left running before it is boxed. Bring the key you already pay for and it works on the first boot.

Compute
67 TOPS
Memory
8 GB
Storage
512 GB
Power draw
20 W
Delivery
Free · 2–5 working days
Returns
30 days, full refund
Subscription
None
Price
€549
Buy €549

EU VAT and delivery included — the number at checkout is the number you pay. Ships from Bulgaria to the EU, UK, Switzerland and Norway. 2-year legal guarantee of conformity.

In the box

  • HermesBox unit, assembled and tested
  • Bring-your-own-key setup for Claude, GPT, Gemini and OpenRouter
  • One-line access to 652 open Agent Skills, and your own
  • Telegram and web access, ready on first boot
  • Ollama and llama.cpp, with local weights already on the drive
  • OpenAI-compatible endpoint for the tools you already use
  • Power supply, Ethernet cable, quick-start card
  • 30-day money-back guarantee

Not ready yet

Not sure it fits your stack?

Get the setup guide — which providers plug in where, what an 8 GB local model actually handles, and a monthly note on what people are automating with theirs.

One email a month at most. No tracking pixels, and unsubscribe from any of them.