Agents that work for hours, and pause when nobody's using them.
Leave a build, a crawl or an agent running in a sandbox. It pauses with its memory when it goes idle and wakes on the next request, so nothing restarts from scratch.
Pause with memory, wake on use
An idle sandbox stops with its memory, so compute isn't billed. The next API call or request to one of its hosted URLs wakes it with its processes still running.
DocsDetach and reattach
Start a command in the background, check its status, and follow its live output from any offset. It survives a stop and resume.
DocsA deadline you set
Auto-stop defaults to an hour. Set any TTL up to 30 days, extend it while it runs, or turn it off.
DocsEvery command on the record
Commands run through the API are kept with their output for 90 days, readable even while the sandbox is stopped.
DocsRun it in the background
id=$(sbx new --ttl 86400 --idle 60 --json | jq -r 'select(.event=="ready") | .id')
pid=$(sbx exec "$id" --detach "./crawl.sh" | jq -r .processId)
sbx exec "$id" --status "$pid" # running? last lines of output
sbx exec "$id" --attach "$pid" # follow it liveMore use cases
Give every agent its own Linux VM with your repo, your keys and a real Docker daemon. Start ten from the same template, prompt them over the API, and keep the ones that worked.
Start a sandbox from your app's template when a PR opens, check out the branch, and post a stable HTTPS link. Reviewers click it; it stops when the PR closes.
Every sandbox has a Linux desktop with Chrome that an agent can see and drive, and that you can watch live in a browser tab.
When your product runs code an LLM wrote or a user uploaded, run it in a VM with its own kernel that can't reach your network, then throw it away.
/dev/kvm is passed through to every sandbox, so QEMU, Firecracker and the Android emulator run with hardware acceleration inside it.
Add https://sandboxer.com/mcp as a connector and sign in. The assistant can then create Linux sandboxes, run commands, move files and put a port on an HTTPS URL, all in microVMs, not on your machine.