Skip to main content
This page is a high-level guide to Sailboxes, efficient cloud environments specifically designed for long-horizon agents. See the Sailbox reference for reference documentation on Sailboxes.

What are Sailboxes and why should I use them?

Sailboxes are persistent Linux VMs designed for long-horizon agents. They can be dynamically provisioned in seconds and are the perfect cloud environment for any agent. They provide a number of advantages over other sandboxing providers:
  • Only pay for the exact portion of CPU, memory, and disk you actually use within a sandbox. Agents spend most of their time blocked on I/O so sailboxes are significantly more cost effective than other providers (see comparison below).
  • Use as much (or as little) compute as you need. Even though you only pay for the resources you actually use, each sailbox is eligible to consume a practically unbounded amount of CPU or memory, ensuring your agents are never bottlenecked on hardware.
  • Fine grained network control and automatic credential injection. Fully isolate your agents from your API keys, and grant permissions seamlessly across swarms of sailboxes.
  • Pause, resume, and fork all sandbox state, including open network connections, for any duration. In-flight work survives the pause with no save/restore code on your side.
  • Automatically sleep Sailboxes while waiting on Sail inference calls.
Sailboxes are currently in beta. APIs and operational behavior may change as we stabilize the product.

Provider comparison

ProvidervCPU priceSleep during inferenceMax runtimeMemory snapshotsNetwork snapshotsLocal NVMe disksDocker-in-DockerStart/resume time
Sailboxes$0.015/actively-used vCPU-hourYesNo fixed limitYesYes, open connections survive for up to 10 minutesYesYes<3s
Modal$0.071/reserved-vCPU-hourNo24 hoursAlphaNoNoAlpha<500ms
E2B$0.0504/reserved-vCPU-hourNo24 hoursYesNoNoYes<1s
Vercel Sandbox$0.128/reserved-vCPU-hourNo5 hoursNoNoYesYes<1s
Daytona$0.0504/reserved-vCPU-hourNoNo fixed limitExperimentalNoYesYes<500ms

Start here

  • Quickstart: create a Sailbox, run commands, expose a service, and clean up.
  • Pricing: understand observed-usage billing dimensions and per-hour rates.
  • Images: choose a base image and build custom images with packages, commands, environment variables, and local files.
  • Networking: expose HTTP services, raw TCP ports, and SSH from a Sailbox.
  • Filesystem: read and write files at runtime, stream large files, and decide what belongs in an image.
  • Lifecycle: checkpoint, start from checkpoint, pause, sleep, resume, upgrade, and terminate Sailboxes.