GENERATIVE MACHINE

A machine that turns ideas into working things.

I wish I had a system for this. GENERATIVE MACHINE turns that fragment of an idea into a working machine. Your own secretary AI runs the other AIs and solves the problem. We help with what one person could not do alone.

WORK

What you can ask for

GENERATIVE SYSTEMS

A machine that keeps generating for you: images, motion, text, and data, made automatically on the schedule you set.

You give the secretary AI
What to make and who uses it. What you already have (documents, data, existing material). A reference for the result. Where it is used.
You get
Your own machine. It runs on the schedule you set, exports what it made each time, and records what it made and why. Output as files, or as a page that opens anywhere.
Running machine
GENERATIVE MACHINE · the nightly job base

NIGHTLY RESEARCH

Your own machine scans the field at night.

You give the secretary AI
Your field and your criteria.
You get
Each morning, what the night's scan of GitHub, papers, and primary sources found. What to adopt and what to skip, each with its reason, kept in a ledger you can read. Once a week, a digest of only the essentials.
Running machine
Evolver Engine, our nightly scan that records why

AUTONOMOUS OPERATIONS

A setup that keeps working while you sleep, within the budget you set.

You give the secretary AI
Where your records live (notes, mail), the routine work to hand over, and what its result should look like.
You get
A secretary AI, nightly jobs, and a window that receives requests, so records, incoming requests, and routine work run on their own. Runs stop at your budget cap and never loop endlessly. Every decision is recorded.
Running machine
The setup that runs AGIAS itself (secretary AI, nightly jobs, a window that receives requests).

HOW

How a request runs
HOW A REQUEST RUNS
01You send what you want to make
↓
02We set the direction. The secretary AI drafts the spec. You confirm it.
↓
03A running prototype, not a slide
↓
04You adjust in chat. Every decision is recorded in the ledger, where you can manage it.
↓
05Delivery: the running machine and its ledger

A nightly check after delivery can be built on request.

method · how the AI is run
Gates
Hooks stop the AI before it acts: a commit with a secret, a delete without a look, a claim without a fact. The gate wins, not the model.
Skills
Repeatable procedures written down once and run the same way every time: release, review, fact-check. The AI follows the sheet, not its mood.
Loops
Nightly runs with a budget cap and a score. Each run is measured against a fixed rubric, and the record decides what changes next.
security
  • You talk to one secretary AI. It coordinates the other models behind the scenes; they never contact you.
  • Nothing leaves without a record.
  • Money and publishing need human approval.

MACHINES

Made and run on GENERATIVE MACHINE

IMAGE MACHINE

Now building · Gen 1

Will learn from the prompts used so far and keep generating images on its own through an image-generation platform.

Use
A steady stream of images in one style: visuals for a venue, a brand, a daily feed.
When
Good when the prompts are already there and the time to run them is not.
PromptsAuto-generate

Evolver Engine

Nightly

Every night it scans GitHub, papers, and primary sources, proposes what to adopt, and records the reason. A line in the ledger before a line of code. Each night's judgment goes into the ledger and informs the next.

Use
Keeping a codebase or a field current without reading everything: it reads at night, a human decides in the morning.
When
Good when new tools and papers appear faster than one person can follow.
AgentsLedger-first

Humans control the AI.
A human decides what to build and when to stop, andeverything is recorded.

Every machine here runs under this rule.

The design philosophy behind AGIAS

Direct

Set the AI's direction

Write the spec. Let the models build. Verify and correct. Every contributing model is named.

Record

Ledger before code

The reason is written before the change. Rejections are kept alongside adoptions.

Manage

Code on GitHub, records in OBSIDIAN

Code is versioned on GitHub. Decisions and records live in the OBSIDIAN vault. The machine and its ledger are handed over at delivery.

NOW BUILDING

What is being built together with the AI.

  • Economy of Love v1.1PaperDOI 10.5281/zenodo.18277860

    A paper written while running these systems. Archived on Zenodo with a DOI. Read on Zenodo →

  • GAIASimulationsince 2022-11-30

    A virtual earth: 195 countries and 80 million people, one hundredth of the real population, built from UN and World Bank statistics. Started in August 2026. Its own calendar began on 2022-11-30 and is still advancing; each day, a panel of 10,000 people decides what it did.

  • IMAGE MACHINENow buildingGen 1

    Will learn from the prompts used so far and keep generating images on its own through an image-generation platform. Gen 1 in development.

  • GENERATIVE MACHINENow buildingautomatic request intake

    The system behind everything here.
    Next: automatic request intake, so a request goes straight to the secretary AI.

PRIVACY

What happens to what you send
  • Your mail and material are kept in the operator's own OBSIDIAN vault and used only for your request.
  • They may be read by the AIs listed under HOW (Claude, Gemini, GPT, and local models) to draft the spec and build. Nothing is published without your approval.
  • Material is kept up to one year after delivery, or deleted earlier on request. The ledger is handed over with the machine.
  • This site sets no cookies and runs no analytics. Only your language choice is kept in your browser.