A research-led product studio

We research AI. Then we ship it.

Artifocial is a studio: our AI agent organization builds and ships focused apps end-to-end. We do the research in the open — read it on the blog and newsletter.

Architecture diagram of the stack Artifocial runs itself on, labelled in the artwork as a diagram rather than a product screenshot. A human board holding approval gates, spend limits and kill switches sits above a control plane running on one machine we own. The control plane routes work to a CEO agent, department leads and two-critic review councils, which run on Claude Code and Hermes worker runtimes, read a git-backed company memory vault before acting, and call models through our own provider keys or open models on our own hardware.

Artifocial Foundry · Installation-verified v0.1.3 MVP

Your company, agent-native. Ready for a guided walkthrough.

Foundry is the same stack we run internally: agent-native operations, on infrastructure you control, with a human board that keeps final decisions in human hands.

We run on it ourselves, daily
Artifocial has operated agent-native on this stack every day since June 2026 — the company that builds Foundry is run by it. Our build-in-public record is the receipt.
The org we actually operate
Foundry is the packaged version of the organisation we run, not a reference architecture drawn on a whiteboard. It improves weekly, because we are the ones living with the rough edges.
One machine you control
Designed to run on a single machine you control. Your company memory, your issue history and your agents stay on hardware you own.
Your board keeps the final say
Approval gates, spend limits and kill switches are how our own governance works, so they are how Foundry ships. Agents propose; humans decide what leaves the building.

It is not a silver bullet, and it improves with the data you give it — the honest list of what Foundry is not is on the Foundry page.

Latest Post

AI Insights & Tutorials

Stay updated with the latest AI news, research papers, and practical tutorials.

Frontier Weights Went Public — With a Price Tag Attached

Frontier Weights Went Public — With a Price Tag Attached

Highlights of AI News for August 10 - 16 2026

The Practitioner Newsletter

Practical ML and AI for people who build — tied to what we actually ship. No hype, no press-release rewrites; the research and engineering behind our apps, in your inbox.

We've folded Build with AI early access into this newsletter. Looking for the free lessons? Start with our practitioner writing on the blog.

Buttondown receives your email, subscription IP, referrer, and subscription time to confirm and deliver the newsletter. Privacy Notice. Unsubscribe at any time.