🚀 AI agents can do real work now. Which is exactly why I won't let one loose on my actual computer: Give every AI agent its own computer. We have built an operating system that makes autonomous agents work better: they operate programs, write code and pipelines, fill in forms, make your job easier. And because every session is sealed inside its own virtual machine, your system and your data stay protected. It's open now: 🔗 get.brainarbeit.com - Install the image on a virtual machine, a spare computer, or Raspberry Pi 5

Brainbox - Give your AI Agent a safe home

AI can work for you - and now it can even shop and pay for you. Agents may have access to all your data and full control of your system. We believe these agents need broad permissions and the freedom to work efficiently, but only with the data and control you choose to grant them. We give the autonomous agents of your choice (Claude, GPT, Ollama, …) a safe home.

The reproducibility crisis has a supplier. More than 18,000 questionable images were found this week across the antibody catalogues of 15 companies. Around 13,800 of them share seven identical backgrounds. That is a technical way of saying the experiment behind the figure was probably never run at all. With doesitreproduce .com, we have spent the past year re-running the bioinformatic pipelines of more than 1,000 published papers, one paper at a time, just to see what actually comes out the other end. It taught us a great deal about where results break. What we missed is that it starts getting difficult much earlier. We treated the paper as the beginning of the chain. We now learn: It isn't. The first piece of evidence is a figure on a product page: the one that decided which antibody was bought, which band was believed, which result ended up in the methods section we were so busy re-running. Nobody peer reviews that figure. It's not a result that fails to reproduce. It's a figure that was never produced. nature.com/articles/d41586-0…

Germany calculates how long its own paperwork should take. For this stack of forms: 37 working days. Brainbox did it in 13 minutes. No API - it just fills the same forms a human would, at scale. What would you do with your day if you never had to fill out a form again?

People used to debug code. Now people debug conclusions. That is a harder job, and a far more human one. AI has quietly removed code errors and the pipeline that used to die now runs to completion. We can re-run a pipeline and check whether it works. Comparing pipelines from mid 2026 with those from a few years ago, we are starting to see the problem shifting quietly: from "does not reproduce at all" to "technically reproduces, but is not plausible."

🍓 All of this has run unattended for months - on a handful of ordinary computers. One of them a Raspberry Pi. No cloud. No data center. No data leaving the building. The whole engine - autonomous agents that select, queue, run, and publish on their own - lives on hardware you could buy this afternoon. That's the point of the Brainarbeit Box: your agents, your data, your machines. Self-hosted, sealed, and about to be open source. Join Brainarbeit and run your own brainbox! 🔗 get. brainarbeit .com #opensource #reproducibility

🛡️ You can't make untrusted code safe. You can only box it in. That's the whole idea behind the system that runs our reproductions. Every agent, every repo, every script runs in its own sealed machine - its own walls, no access to your data, no open door to the network. If something in there goes wrong - a malicious script, an AI agent off the rails - the damage stops at the walls. Nothing leaks out. Nothing else is touched. Most security tries to spot bad behavior. This just assumes everything might be hostile, and contains it. That's the Brainarbeit Box. Source opens August 9. 🔗 get. brainarbeit. com #opensource #AIsafety