[10] Runtime & deploy · required/ How you run it

Runtime & deploy for AI agents

Where it runs, and whether it survives a restart.

8 options tracked · 4 open source · 4 self-hostable · required in every stack

· All 8 options/ Compare
OptionWhat it doesLicenceSelf-host
Docker ComposeOne file, one box, everything local. The honest starting point.Open sourceYes
VercelStreaming-friendly serverless for TypeScript agents with a web front end.ProprietaryNo
Cloudflare WorkersEdge runtime with Durable Objects for long-lived, stateful agent sessions.ProprietaryNo
ModalPython-native serverless with GPUs and sandboxes, scale to zero.ProprietaryNo
Fly.ioLong-running containers close to users, without owning a Kubernetes cluster.ProprietaryNo
TemporalDurable execution — the run survives a crash, a deploy and a week of waiting.Open sourceYes
CentaurParadigm's self-hosted control plane: one shared team agent, an isolated k8s sandbox per Slack thread, and no raw API keys in the agent's environment.Open sourceYes
KubernetesYour existing cluster. Nothing new for the platform team to approve.Open sourceYes
· Head to head/ 28 comparisons
· Common questions/ FAQ

What is the runtime & deploy layer of an AI agent?

Where it runs, and whether it survives a restart. Every stack needs one — it is not optional.

How many runtime & deploy options are there?

This registry tracks 8. 4 are open source and 4 can run on your own infrastructure.

Which runtime & deploy option should I choose?

It depends on constraints rather than preference: whether you must self-host, whether the budget allows a hosted service, and which language your team writes. Describe what you are building and the advisor fills this layer along with the other 9.

· The other 9 layers/ Keep going
· For agents/ This page, machine-readable

Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.

curl -s -H "Accept: text/markdown" https://newagent.build/layers/runtime