Blog
How Zode works, and how to run coding agents and CI on machines of their own. Follow along by RSS.
We raised our pre-seed to build computers for agents
Agents don't belong on your laptop, and every pull request they open runs up your CI bill. We raised our pre-seed round to give them machines of their own.
Your coding agent shouldn't be holding your API keys
Everything that runs in an agent's VM can read the keys you gave it, and 2025's npm attacks went looking for exactly those. Why the usual fixes fall short, and what we do instead.
Run Claude Code in a cloud VM, on your plan
Give Claude Code its own Linux VM in the cloud, signed in with your Claude plan, while the token stays outside the VM. Install, sign in, hand it a task, fork it.
Faster GitHub Actions runners in one line
Change runs-on and a GitHub Actions job runs on Zode: standby runners, warm caches kept between jobs and a local Actions cache. The trust rules, and where it's slower.
Fork a running VM: how live forks work
A fork copies a running VM, memory included, so its processes carry on in both copies. How copy-on-write forks work, why each needs fresh randomness, fork vs snapshot.
Containers or microVMs for AI agent sandboxes
Containers share a kernel, microVMs don't, and coding agents need more than either gives by default. Isolation, Docker inside, state and network for agent sandboxes.
Keep API keys out of your AI agent's sandbox
A coding agent can read every key in its environment. Why that matters, what scoped keys miss, and how a host-side placeholder swap keeps real keys out of the VM.