Skip to content

Bay Area on-site · remote nationwide

Your personal AI agent, set up properly — and locked down.

We install, harden, and maintain self-hosted AI agents for people and small businesses. The install is the easy part. Doing it without handing away your inbox is the job.

Limited founding spots available $500 personal setup, normally $749

Why this needs doing carefully

The install takes twenty minutes. That is not the hard part.

An agent worth having can read your email, send messages as you, and run commands on your machine. That is the whole point of it — and it is also the entire problem.

01

Your keys sit in plaintext

Out of the box, the agent runtime stores your model API key and a token for every messaging account you connect as readable text on disk. Anything that can read that file owns your accounts.

02

A webpage can give it orders

Prompt injection is unsolved. Instructions hidden in an email signature, a calendar invite, or a page you asked it to summarise can be followed as though you had typed them yourself.

03

The default install faces the internet

The management port is frequently left exposed. Published advisories this year cover remote compromise and data exfiltration, and one breach exposed email archives from 41 organisations.

None of this means you should not run one. It means somebody should close those doors before you connect your accounts. Here is exactly what we close, and how →

How it works

Three steps, about a week.

One

Strategy session

An hour. We map how you actually work, decide what an agent should take off your plate, and put a real number on what it costs to run. You leave with a plan whether or not you build it with us.

Two

Build and harden

We install on your hardware, connect your channels, and apply the full hardening baseline. You watch if you want to. Your machine is backed up before we touch it.

Three

Handoff

A live walkthrough, a written map of everything your agent can reach, and a kill switch you can hit in five seconds. Then 14 days to ask anything.

What it costs

Prices, in public.

Full pricing and what runs monthly →

Everyone else in this category makes you book a call to find out. We would rather you knew now whether we are in your range.

Personal Agent Setup

Most booked

Individuals and solo professionals

$500 $749

one-time · 2-hour working session

Founding rate — first 10 clients, in exchange for a testimonial and a written case study.

A working, hardened personal agent on your own hardware — and the documentation to understand what it can reach.

  • Installed on your hardware — Mac Mini, spare laptop, or a VPS
  • Model provider connected, with hard spend caps configured
  • Two to three messaging channels wired up
  • Credentials moved out of plaintext into your system keychain
  • + 7 more
Claim a founding slot

Agent + Workflows

Professionals with repeat workflows worth automating

$1,500–$2,500

one-time

Everything above, plus the agent is taught to do the specific work that eats your week.

  • Everything in Personal Agent Setup
  • Two to three custom skills built around your actual work
  • Integration with the tools you already use
  • Inbox triage, meeting prep, research briefs, or whatever your bottleneck is
  • + 2 more
Discuss scope

Business Deployment

Teams of 5–50

$5,000–$15,000

project

A multi-user deployment with a written threat model — because now it touches other people’s data, not just yours.

  • Multi-user gateway deployment
  • Written threat model and isolation architecture
  • Security review documented for your records
  • Admin training for one or two staff
  • + 4 more
Request a scoping call

No surprises

What it costs you after we leave.

These bills go to you, not through us. We take no margin on your API spend, and we configure hard caps during setup so it cannot run away.

Hardware
$0 – $799 once
Reuse a spare machine and this is free. A new Mac Mini runs $499–$799. A VPS is $5–$20 per month instead.
Model API
$10 – $50 / mo
Personal use at 50–100 messages a day. We configure spend caps during setup so it cannot run away from you.
Model API — business
$50 – $300 / mo
Team usage across multiple seats and heavier automated workflows.
Our software
$0
The agent runtimes we deploy are open source. We do not resell them and we take no margin on your API spend.

Not sure which of these you need?

Start with a strategy session. An hour, $125, and you leave knowing what an agent would do for your week, what it would cost to run, and whether it is worth doing yet — including if the honest answer is not now.