The All-Purpose Engineer

I grew up in the Silicon Valley of California watching Macguyver, taking things apart and building with legos. Thirsty for knowledge, my skillset is in finding paths others haven't, in solving problems that have never been solved or in making things that have never been made before. I'm thirsty for learnin' and I grew up a reclusive nerd so that you didn't have to. I've built my life around making ideas into reality and having fun along the way.

I'm guessing you have a cool idea. An app? A product? An interactive art piece for Burning Man? ... Do you need a project managed? Do you need someone for whom there is no title to help create something new and different? That's exactly where I come in. I want to help you turn your weird idea into weird reality. So.

Tell me what you want to build

You Need Your Own Agent

Most people are renting AI by the API call but there's a problem with that: it works right up until the bill doesn't, or the provider changes the rules, or your data's sitting on someone else's server doing someone else's math. I got tired of that math. So I built an agent that lives on your machine — it has memory, it has a whole toolbelt, and it talks to whatever it needs to talk to, including my own CRM (SeedlingCRM) if that's your flavor of chaos.

Agents like this are where all of this is headed... anyone still renting their intelligence by the token in five years is going to feel it. Might as well own yours now. I built it, I'll help you run it, and yeah, I think it's pretty rad.

Power

Full toolbelt out of the box: CRM access, email (read/draft/send, gated for safety), web research, image generation, long-term memory, and a growing set of workflows for sales, marketing, and daily ops. Not a chatbot — an actual coworker.

Cost

Run it fully local and it's free to operate — no per-token bill, ever. Point it at Claude instead when you want more horsepower for a hard problem, billed to your own API key, your own budget, your own call.

Your Data

Everything it remembers, drafts, and generates lives on your machine. Nothing shipped off to train someone else's model. You see every tool it has, and every tool it's about to use before it uses it.

Capabilities

CRM & ops, email triage & drafting, research, image generation with saved style presets, a browser dashboard with chat history — and it grows. New tools and workflows ship regularly, and add-ons let you bolt on more.

Claude, or fully local — your call

Claude backend

Smarter reasoning for harder problems. Billed to your own Anthropic key — you control the spend limit, and nothing runs through me.

Local backend

Runs on Ollama, entirely on your machine. Free, private, and switchable live from the dashboard — flip between the two whenever a task calls for it.

A note on hardware

This is a full agent — it does real work (CRM access, email, image generation, memory), not just chat. Running it locally is free and private, but its speed and the size of model it can comfortably run depends on your machine. No good GPU? No problem — point it at Claude instead, which runs in the cloud and costs only pennies per use, so hardware stops mattering entirely.

Tier	RAM	GPU	What you get
Minimum	8GB	Any / none	Use the Claude backend — no local GPU needed at all. Local mode works too, just with a smaller/slower model.
Recommended	16GB+	8–12GB VRAM (e.g. RTX 3060/4060/5070)	Comfortable local 14B-class models, responsive dashboard, image generation works well.
High-end	32GB+	16GB+ VRAM (RTX 4080/5080/5090, or 32GB+ unified memory on Apple Silicon)	Bigger local models, image generation and local chat running at once without competing for memory.

Not sure which you have? Any Windows/Mac machine from the last few years handles the Claude backend fine — the table above only matters if you want to run models locally for free.

Get Your Own Agent

How Buying One Works

1

Select a plan

One-time or monthly — pick what fits. Add any plugins you want at the same time, or later.

2

Get your license & download

Checkout issues your license key instantly. Download the agent from your account any time a new version ships.

3

Run the setup wizard

A short wizard asks a few questions — your CRM connection, agent name, which backend — and writes your config. No manual file editing required.

4

I'll help if you're stuck

Setup help is available as an add-on — I'll get on a call and get it running with you, not just point you at docs.

See Plans & Pricing

Steve Peak

With decades of experience leading or working in dozens of teams in many countries, projects and fields... I am an All-purpose Engineer. A renniasance man of action... and I want to help you build your next project.