Customers

The teams running their agents on Sandal.

Sandal came out of building Enter, an app that runs coding agents on every device. No sandbox we tried kept up with what those agents actually needed, so we built the one they run on today. Here is that story, and the teams that followed.

EnterCustomer story

Enter gave every coding agent its own machine. We built Sandal to do it.

Coding agents on desktop, mobile and cloud. Sandal started as the execution layer inside Enter before it became its own product.

Enter
Read the story
12,400+Machines launched
4.2sAvg startup time
6.8hAvg agent runtime
Products

The products Enter runs on.

Every surface in the story is one primitive, a microVM with its own kernel, behind one API. These are the four Enter uses every day.

Live desktop stream
CodeFileEditSelectionViewGoTerminalWindowHelpWed 16:45
agent.py · sandbox
Explorersandboxagent.pybrowser.pyvision.pytestsREADME.md

1from sandal import Sandbox

2

3# boot a desktop the agent can see

4vm = Sandbox.create(desktop=True)

5vm.screenshot("before.png")

6

7vm.click(x=412, y=280)

8vm.type("hello from the agent")

9vm.key("cmd+s")

10

11# read the screen back

12frame = vm.stream.latest()

13assert frame.contains("Saved")

zsh, sandal

➜ sandbox sandal desktop --stream

connecting to vm_7c31…

✓ stream open · 60fps · 18ms latency

screenshot → before.png

click(412, 280) · type · cmd+s

✓ saved

➜ sandbox

60fps
Customer stories

In their own words.

There are impacts you can measure, and then there is the moment a team stops thinking about where its agents run.

Your turn

Give your agents the machines Enter runs on.

Own kernel each, under a second to create, free while paused. Linux, macOS, Windows, iOS simulators and GitHub runners behind one API.

npx sandal init