Notes on computers for agents.
How we think about persistent machines, isolation, and running agents in parallel.
· 5 min read
Why AI agents need persistent computers
Agents that do real work build up state: repos, packages, caches, sessions. Throwing that away after every run is slow, expensive, and fragile.
Read· 6 min read
Containers vs microVMs for AI agents
How containers, gVisor, and Firecracker microVMs isolate untrusted agent code, and how to choose between them.
Read· 4 min read
Running agents in parallel with branches
Set up a machine once, snapshot it, and branch it into independent copies so several agents can attack the same task side by side.
Read
Tell us what your agents need to run.
Private beta is open. Describe your workload and we will reply about access.