I'm the developer of Velo Workspaces, a native macOS app for disposable Linux and macOS VMs on Apple...
Michael
Posted on Sep 9
AI-assisted
I'm the developer of Velo Workspaces, a native macOS app for disposable Linux and macOS VMs on Apple Silicon. This post is about a specific problem I kept hitting while building it, how to let an AI agent run generated code safely in a VM without giving up the GPU acceleration? I ended up with the architecture AI Bridge based on vsock, and supported by real benchmark numbers.
The problem
A Japanese version of this is on Note. An increasing number of engineers and creators are running...
A deep dive into how Cloudflare, Docker, Azure, and AWS are securing autonomous AI agents using advanced microVM sandboxing.
Linux distributions come with options for process isolation. This article shows how to use microVMs to run AI coding agents.
OwO What's this? 💨✨ A tiny but mighty Mac mini M4 🍎⚡ with 16GB RAM, lots of local AI models 🤖🧠, and...
What I built Atlarix — a ~400MB AI agent workstation that sits beside your IDE (VS Code,...
Headline: Vercel Sandbox runs untrusted code — including code a model just wrote — inside an...
