Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents
Hey HN, I’m Vishnu from Agent37 (https://agent37.com). We build sandboxes for running AI agents at under 10% of the cost of most sandbox providers. Our customers spend an average of $0.37/month per sandbox. You can view a video walkthrough of the product here: https://youtu.be/DK5ISR2tbNo We started as one of those OpenClaw wrapper companies back in February (yup.. judge me). In time we added more and more harnesses. One of the goals I had at the time was to offer a free plan to users, so as to gain more market share. But it was too cost prohibitive to do it right away. Especially since we were bootstrapped and servers were running on my savings. Today we’re actually able to offer the free plan thanks to the optimizations we’ve made since. Over 90% of the new signups we have are just free plan users and they host their personal Hermes/Openclaw/Claude Code etc on our cloud. Our infrastructure cost for the free sandboxes averages around $0.05 to $0.10 per user per month. Here are some techniques that have worked for lowering cost: * When you look at agent harnesses, they have certain patterns in the way they consume CPU and RAM. They need CPU in bursts when they’re initializing or performing certain tasks, but beyond that, they’re often not peaking. They need more RAM for things like browser and computer-use tasks. Once the task is done, usage often comes back down. This is a key insight in lowering cost, so by efficiently managing the CPU/RAM utilization we could lower the cost. * Secondly, you have to skip the hyperscalers when renting the Hosts. I worked at Amazon before and they have 80-90% margins on VMs. So it was an obvious choice once I looked at the prices to go one layer down to vendors like Hetzner and OVH. This alone was probably one of the biggest cost levers in reducing the cost. * Thirdly, you also want to pick a technology stack that lets you efficiently cache and share resources across the host. We use gVisor for better utilization and fast boot times. It lets us use available host memory across sandboxes without reserving a full VM’s memory for each one. There are tradeoffs: our gVisor sandboxes don’t support workloads like Docker-in-Docker or Android emulators. * And finally the size and shape of the hosts you buy also makes a big difference. RAM is typically the bottleneck when it comes to cost and not the CPU. This is specifically true for agent harness workloads, so when buying servers, we optimize for packing more RAM into a given host. We also host full VM sandboxes for workloads that need them, including running Docker at a slightly higher price, but they are still pretty low cost given the rest of the techniques. Overall, my learning has been that just by focusing on a niche of sandbox usecases, and optimizing for it you can give a much better cost/performance tradeoff. I was previously a Senior Software Engineer at Amazon and an Engineering Manager at Quantcast. I built Amazon's internal AI chatbot, Diya, and their internal coding harness, Ziya. If you’re someone who’s looking to run agents on sandbox and are exploring a sandbox vendor, come check us out. We’re particularly looking for developers building messaging agents to try their workloads and challenge the limits and economics of our platform. Thanks! https://agent37.com
Comments
5 preview comments · loading full threadLog in to h4cker, then connect Hacker News to publish comments.
Congrats on the launch! Very exciting! You guys are operating in a very competitive space. This stuff is fun to build, so a lot of engineers will end up building it. Not to discourage you, but I suspect it will be difficult to capture much value selling this offering as its going to be race to the bottom against very well funded alternatives that can sell these features at a loss in order to get you to use their databases and other offerings that are higher margin and stickier. As you guys learn more about how to take this sort of technology to market, you may consider trying to get closer to the actual work that people actually need these agents to do. What can you do better because you have this technology? For example, I work in healthcare administration and we have built our own agent sandbox infrastructure on top of firecracker microvms that solve similar use cases as Agent37. We will never sell it. It's part of our competitive advantage for doing healthcare tasks. Food for thought! Good luck!
I've been looking at offloading local work from my MacBook Pro (M1 Pro / 32 GB) specifically because I've been working with a lot of Android apps and emulation is killing me on top of everything else that I'm running. Got a bunch of Daytona credits which are close to useless given their restrictions until you hit tier 3. You seem like you're actually slightly cheaper than https://boat.dev/ but with less storage? That's the closest to your pricing unless I'm mistaken. Any other insight as to differences between you two? Also I'll add you to a list I've been maintaining of sandbox providers, congrats on the launch! https://engine.build/lab/agent-sandboxes
Sandboxes look a bit commoditized. You cannot 10x on basically what's just a VM with a few agent-friendly features in 2026. Hence competing on purely price as a new startup is a bad idea imo. As you mentioned hyperscalers have insane margins, but if this turns out to be a real market, they will lower cost, even just eat the loss if they want and take you out of business. Without any hardware innovation, it's tough for me to see this working. If you are going with a customization angle, again, no moat and plenty of competitors
The host isolation everyone is comparing on price is not the hard problem. gVisor vs a full VM is a real tradeoff. Most agent failures that actually hurt are not sandbox escapes. They are the agent acting as you with a coarse OAuth grant, or reading a secret that was sitting in the environment. A cheaper box does not fix that. You still need an egress allowlist the guest cannot rewrite, credentials that never enter the guest, and a hard call budget per task. I would pay more for that broker layer than for another 2x cheaper sandbox.
This is really impressive work on the infrastructure side. Skipping hyperscalers like AWS for Hetzner/OVH is definitely a massive lever, but your choice of gVisor for memory overcommit is where this gets technically interesting. A few questions on the implementation: • Memory & Density: Since gVisor allows you to share memory without reserving a full VM's allocation, how are you handling noisy neighbors if multiple sandboxes spike in RAM usage simultaneously? Are you using specific cgroups configurations or out-of-memory (OOM) killer tuning to prevent one sandbox from crashing the host? • Storage Persistence: You mentioned that files stay with the agent across sessions. How are you handling the storage layer efficiently at $0.05–$0.10/user? Are you using localized NVMe storage with networked backups, or something like ceph/block storage? • Cold Starts: When a sandbox wakes up from auto-sleep, what is the exact latency for the user? Congrats on the launch and the pivot from a simple wrapper to a real infrastructure play!