In stock · ships in 2–5 working days

Your AI agent shouldn't
live in a browser tab.

HermesBox is a small always-on machine that runs your assistant on your desk. Plug in the Claude, GPT or Gemini key you already pay for — it uses your plan, your provider bills you, we take nothing. Local models for the work you'd rather not send anywhere.

  • In stock · ships in 2–5 days
  • No markup on your tokens
  • 30 days to send it back
ClaudeGPTGemini300+ modelsLlama 3.1 8BQwen 2.5 7BMistral 7BDeepSeek-R1 Distill 8BGemma 2 9BClaudeGPTGemini300+ modelsLlama 3.1 8BQwen 2.5 7BMistral 7BDeepSeek-R1 Distill 8BGemma 2 9B
Why local

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's 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're paying for a capability that's only awake when you are.

02

You're already paying twice

A Claude plan. A GPT plan. Then some agent service on top 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 part by hand instead.

Bring your own key

The subscriptions you already pay for, already working here.

This is the part people underestimate. HermesBox is not a small model pretending to be a big one — it's the machine your agent lives on, pointed at whichever provider you already have a relationship with.

ClaudeAnthropic

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

GPTOpenAI

Drop in the key you already use for everything else.

GeminiGoogle

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

300+ modelsOpenRouter

One key, the whole catalogue, switchable per task.

Localon device

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

Anything else with an OpenAI-compatible endpoint drops in the same way.

hermes providers
anthropicclaudeyour key · your plan
openaigptyour key · your plan
googlegeminiyour key · your plan
openrouter300+ modelsyour key · your plan
ollamalocalon this box · no key
monthly cost added by hermesbox: €0.00

We are not in the token business

Most things that sit between you and a model take a cut, or resell you capacity at a markup, or make you buy credits in their currency. This doesn't. Your key goes in, the box calls the provider directly, and the invoice arrives from Anthropic or OpenAI exactly as it did last month.

We sold you a computer once. That's the entire commercial relationship.

Our cut of your tokens
0%
Required subscription
None
What it gets pointed at
  • 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
And what it already knows how to do
Agent Skills · open ecosystem
652skills,
free to install

A skill is how it learns a specific job

Filling a PDF properly. Cleaning a spreadsheet the way an accountant would. Reviewing a diff. Each one is a small folder of instructions your agent reads when the job comes up — so it stops guessing at the shape of the work and just does it the known-good way.

01
One line each
No config file to hand-write, no restart. Ask for it in Telegram and the box goes and gets it.
02
Plain folders of Markdown
Read a skill before you install it and edit it after. Nothing is compiled, encrypted or phoning home.
03
Your own count too
Drop a folder of your own instructions in and it behaves exactly like the other 652.
A sample from the library12 of 652
  • pdf
  • xlsx
  • docx
  • pptx
  • mcp-builder
  • webapp-testing
  • brand-guidelines
  • frontend-design
  • artifacts-builder
  • canvas-design
  • internal-comms
  • skill-creator
  • + 640 more

They run on whichever provider you pointed the box at — a skill that reads a contract can run against the local model and never leave the room, and the same skill can run on Claude tomorrow because you changed your mind, not because we changed our terms.

What one is, in full
pdf/
├── SKILL.md       ← what to do, in English
├── reference.md  ← the fiddly bits
└── scripts/      ← optional helpers
$ hermes skills add pdf

Or just ask it in Telegram — same thing, fewer keystrokes

One payment, then nothing

Buy the box, plug in the keys you already have, and never pay us again. If it isn't what you wanted, send it back inside thirty days for every cent — no form, no phone call.

The HermesBox unit photographed from above, showing the ventilation fins and cooling fan.In stockActual unit · not a render

HermesBox

Your AI agent, on hardware you own.

€549

One-time payment. VAT and shipping included — no subscription, ever.

Free delivery in 2–5 working days — dispatched from Bulgaria to the EU, UK, Switzerland and Norway.

Secured by Stripe
  • 30 days to send it back, in full
  • No account, no subscription
  • We take 0% of your tokens
  • Ships already assembled and tested
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

In stock. Dispatched from Bulgaria within 2–5 working days to the EU, UK, Switzerland and Norway. Shipping and EU VAT are included — the number above is the number you pay. Model usage is billed by your own provider on your own key; we add nothing to it and there is no subscription to us.

As a consumer you have a statutory right to withdraw within 14 days of delivery; we extend that to 30. A 2-year legal guarantee of conformity applies on top. Terms of sale · Privacy

Why us

We built this because we were paying three companies for one job.

A Claude plan. A GPT plan. And then a third invoice, every month, from a service whose entire contribution was keeping a process running while we slept — using the keys we'd already paid for.

That third invoice is a computer. So we made the computer, sold it once, and stayed out of the token business entirely.

Also ours

We build the same box under a second name. clawbox.com sells the hardware on its own, for people who want the machine without the agent build on top. Same company, same workshop, same thermals — so if you have read one of these pages, you have read most of the other.

Check your own invoice

The cleanest audit there is: buy the box, run a week of work through it, then open your Anthropic or OpenAI billing page. What you see there is what you paid. Nothing routes through us, so there's nothing for us to skim.

Nothing here is proprietary

Ollama, llama.cpp, open weights, an OpenAI-compatible endpoint, your own API keys. Every piece is something you could assemble yourself — we just did the assembling, the thermals and the enclosure.

The money is reversible

Thirty days from the day it lands. Which means the most you can lose by being wrong about us is the postage back.

The 90-Second Setup

Three steps. Then it's just there.

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

Setting up a HermesBox, start to finishNothing loads from YouTube until you press play
01

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.

02

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.

03

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.

hermes.localoffline

Same box, both routes — cloud when it helps, local when it matters

The hardware

Small, specific, and entirely yours.

A Jetson Orin Nano Super with the models already on the drive. It draws less than the lamp next to it and does nothing else with its life.

The HermesBox unit photographed from above, showing the ventilation fins and cooling fan.
Pre-production unitActual photograph
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

Eight gigabytes is the honest constraint here: it runs 7–8B models at four-bit comfortably, and it does not run a 70B. If your work needs a frontier model, this is the wrong machine and we'd rather you knew that now than after it arrived.

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, 19 watts
The work you can't upload
Goes up anyway, or not at all
Stays on the local model
If they change the terms
You migrate, on their schedule
You already own the machine

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

Ownership

Nobody is listening
on the other end.

No account to sign into. No terms that quietly change. No model swapped underneath you on a Tuesday. It's a computer, you bought it, and it does what you tell it — in your room, with the door shut.

The HermesBox Promise

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

Buying hardware from a company you'd never heard of this morning is a leap. These are the terms that make it a small one.

01

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.

02

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.

03

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.

04

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.

If nothing changes
  • Two AI subscriptions, and a third service reselling you the same tokens
  • Work that only happens while the laptop is open and you're watching it
  • The sensitive half of the job still done by hand
With one on your shelf
  • The plans you already pay for, running on a machine you own outright
  • It works through the night and messages you when it's done
  • The documents you'd never upload stay on the box, answered anyway

Own the machine
you think with.

One payment. One box. Your keys, your provider, your invoice — and a machine that keeps working after you've gone to bed.

In stock · 30 days to send it back

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.

Still unsure? Ask us directly — a person answers.

Not buying today

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 · unsubscribe in one click