Where we share what we learn building smol machines, and how we think about computers, AI agents and the infrastructure they run on.
e2e can now run every test attempt in its own branch of a warm, signed-in browser machine. Retries start clean, sign-in happens once, and each attempt can get its own copy of the app.
Writing software keeps getting cheaper, and running it does not. Why we built one machine primitive, and how it gets more out of the hardware that already exists.
We open sourced smolvm, the runtime under smol cloud, and the tools that manage it. Here is why, and what customers pay us for instead.
Harbor, the harness behind Terminal-Bench 2.0, can run every trial in its own VM embedded in Harbor's process. We measured it against Apple's container tool on one MacBook: 1.3 seconds per trial against 21.
AI agents work on real computers, and computers have no undo. smol machines checkpoints an agent's whole machine, so it can undo a bad step, go back to any earlier point or try several paths at once.
Recent merges give a smolvm guest a GPU without passing one through: the guest carries no driver, only drop-in CUDA shim libraries that forward calls over vsock to a host that owns the GPU. Here is how API remoting works and how it stacks up against passthrough, vGPU, and container device injection.
The newest release runs k3d inside a single machine. Kubernetes is one of the most demanding things you can ask a Linux environment to host. Here is why a microVM can and a container cannot, and the one device node the kubelet refused to start without.