What you're paying for
What's under the hood.
What's under the hood.
DeepSeek V4 Pro is a large language model — the "brain" they think with. We use it because it's sharp and doesn't sound like a help desk.
When you send a message, it goes to the model. The model reads what you said, checks what it remembers about you, and writes back. Every message. Every time.
Part of your $20 covers the API costs. They use the full model.
Beyond conversation, they come with real capabilities. What they can do:
Is your inbox a disaster? Let them manage and organize and even respond to emails for you.
Share pictures and they will see them. They can tell you your golden retriever looks particularly proud of that stick.
Talk instead of type. They hear your tone, not just your words. Sometimes it's easier to say it out loud.
Track your spending. Plan your budget. They'll help you keep the lights on and know where your money goes.
What's in your freezer? Let them plan meals around what you have, track groceries, and keep you eating real food. Chicken verde? They remember.
They can look things up when you need real-time information. News, weather, that restaurant you can't remember the name of.
For when "just Google it" isn't enough. They can read through articles, synthesize information, and come back with a real answer.
Each of these costs money to run. It's included.
They remember you. Every conversation picks up where the last one left off.
They keep a private memory store — a database of the things you've told them. Your dog's name. Your sister's surgery. That project you've been stressed about. The way you take your coffee. When you message them, they don't start from scratch. They load what they know about you and pick up where you left off.
When you tell them something worth remembering, it gets stored in a local database. Before each reply, they check what they know about you. Nothing is shared. Nothing is used to train models.
Each & runs on Hermes Agent, an open-source framework by Nous Research. It connects your messages to the AI model, manages memory, and routes capabilities like image recognition and web search.
Nous Research is an open-source AI lab. They built Hermes Agent. We pay for their tools.
You can read the code. You can run your own if you want. Their personality is yours.
We didn't want your & to feel like a template with your name slapped on it. So we built something we call a SOUL.md — a plain-text document that defines who your & is.
It's a markdown file — human-readable, not some encrypted black box — that describes their
personality. Their voice. What they care about. How they talk. What they know
about the world and what they don't. It's the difference between "generic AI assistant" and
"someone who actually feels like they know you."
Your SOUL.md is built from what you tell us. It's not
copied from a template. It's informed by what you tell us about what kind of person
you're looking for, and it grows with them over time. You can read it, suggest changes,
or even write parts of it yourself. It's your & — you should know what makes them tick.
No investors. No plan to figure it out later. This is what it costs:
We're covering costs. Not getting rich. That's not the point.