Always-on machines for bursty work
Agents spend most of a session waiting on a model, a test run, or a person. A long-lived VM bills for every idle minute.
Isolated virtual machines for your AI agent infrastructure. Each MicroVM runs your container image with its own kernel, typically starts in under a second, pauses when idle, and resumes where it left off. You pay for compute only while it runs.
Agents spend most of a session waiting on a model, a test run, or a person. A long-lived VM bills for every idle minute.
Agents run code nobody has reviewed. Containers share the host kernel, which is a weaker boundary for code you don’t trust.
Doing it yourself means fleet management, snapshots, pause and resume, per-tenant isolation, placement, and recovery. That is time not spent on your product.
MicroVMs give you the virtual machine and its full lifecycle, through the Control Panel, doctl, or the API. Because these environments can instantly pause when the AI is thinking or waiting, you only pay for the seconds when the system is actually working. Plus, you can bring your own custom harness and keep granular, kernel-level sandbox control without stitching hypervisors together.
Bring your own container image and run it in its own VM, with its own kernel and a hardware-virtualized boundary.
Set an idle timeout. A paused MicroVM stops compute billing and typically resumes in under a second on the next request, with memory, files, and running processes preserved.
Set up an environment once, checkpoint it, and start new MicroVMs from that state.
Each MicroVM gets its own HTTPS endpoint, configured to require a valid DigitalOcean API token for access. Only requests with a valid DigitalOcean API token can reach it.
Run MicroVMs inside your VPC to reach databases and internal services over private networking rather than the public internet. If you don’t have a VPC, DigitalOcean can create one for you. Add a NAT gateway to the VPC if your MicroVMs need internet access; NAT gateways are billed separately at standard rates.
If a workload crashes after it starts, the MicroVM restarts it automatically, up to the retry limit described in the Documentation, after which retries stop.
Run a command or open an interactive terminal inside a running MicroVM.
One MicroVM per session, paused while the agent waits.
Run AI-generated or user-submitted code in its own VM, alongside your own controls and review.
Start every run from the same checkpoint, with the same memory and disk.
Give every pipeline job a fresh VM with its own kernel. Each job starts from a fresh VM, and the VM is terminated when the job ends.
Package your agent, toolchain, and dependencies as a container image.
From the Control Panel, doctl, or the API.
Reach your workload through its authenticated HTTPS endpoint.
Idle MicroVMs pause and resume on the next request.
doctl compute microvm create my-agent-session \ --oci-ref registry.digitalocean.com/your-team/agent:latest \ --region mkc1 \ --cpu 2 --memory 4096 \ --http-port 8080Run MicroVMs next to the rest of DigitalOcean.
MicroVMs power DigitalOcean Managed Agents. Use Managed Agents if you want the agent runtime managed for you.
Keep agent compute close to the models it calls.
Store the images your MicroVMs run.
Connect MicroVMs privately to your databases and services.
Create your first MicroVM in minutes from the Control Panel, doctl, or the API.