box
Simple computers for agent w/ full VMs
384 followers
Simple computers for agent w/ full VMs
384 followers
Box offers the simplest, cheapest cloud computers for agents, thought for builders of agentic platforms & software factories. Run 'box new' in your terminal, in 2s get a beefy ubuntu VM, with admin rights, a desktop, ssh access. At $0.036/hr it is 10x less expensive than the likes of E2B, Daytona, Modal, so you can run more agents, or run them longer. Run up to 1000 concurrent boxes fully self-served, or ask us for more, with same-day support from the founders.
Free Options
Launch Team / Built With
Customer.ioAutomate Messaging Everywhere — Startups Get 12 Months Free
Promoted
The 2s-to-VM claim caught my eye — that's the number that matters for agent workloads. Question: can you snapshot a warm VM and fork it? The pattern I keep hitting is N agents that all need the same base environment (deps installed, repo cloned) — cold-booting each one wastes most of the cost advantage. If 'box new --from-snapshot' exists, that's the killer feature. Congrats on the launch.
$0.036/hr for a full VM with admin rights is a wild undercut of E2B/Daytona - what's actually different on the infra side that gets you there, bare metal instead of nested virtualization, oversubscribed hosts, or just thinner margins for now? asking because a price that much lower than everyone else usually means either a real efficiency win or something that gets quietly walked back once you're past the free/intro tier.
the isolation questions above are the ones I'd want answered before trusting this with anything real, but the one nobody's asked yet is billing-side: at $0.036/hr an agent that hangs or loops instead of exiting cleanly is cheap per hour but not necessarily cheap per incident if nobody's watching it. is there an auto-kill on idle/runaway processes, a hard spend cap per box, or is the ephemeral-and-cheap pricing itself the safety net and you're expected to monitor it yourself?
Very cool product. Having deployed at scale, most agent sandbox pain is re-provisioning, not compute. Curious how fast fork actually is under load. The persistent-VM + fork-from-snapshot combo is the part that actually changes how you build agent loops.
@aidan_codefox So many hard problems to solve in that space for so many different usecase.
We catter best to long running agent whose data is precious and never to be lost
Congrats on the launch!
As agents move into enterprise workflows, how are you thinking about secure access to private networks, internal systems, identity, and policy, not just the execution environment itself?
Full VM per agent is smart approach. Isolation at that level removes a lot of headaches with shared state. Whats the cold start time like when spinning up a new box?
Brandon's "procurement cycles don't care how fast your model iterates" line hit hard — that's WinBidIQ's whole world, just for federal contracts instead of compute. Skipping procurement is the pitch here, but does any customer ever need a security review anyway before spinning up VMs with admin rights?