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!
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!
But eventually I see us all moving in slightly different spaces as we specialize.
The promise of really cheap AI sounds amazing and is amazing. People will happily accept and engage with "free stuff"; but, I presume you are not starting a business to give away free stuff. Unless you have some model that let's you capture value some other way. e.g. Meta just gave everyone a small computer for free with Muse. Or have some sustainable price advantage on the underlying compute e.g. you are nvidia and make it yourself at scale.
I think you deserve to be compensated for your work! It's hard to make a sustainable business when selling something that costs $5 a month to developers (just seeing your calculator). There aren't that many of us, and AWS/GCP/Azure/Cloudflare have our credit cards already. If it were me, I'd be trying to figure out how to charge more and sell the value of the work you are enabling your customers to accomplish, not the cost of the underlying electrons.
Keep it up!
Compare the two yourself and judge(latter is written in gpt-6 luna).
> One client is one API call. It comes back as an always-on Hermes agent that holds that client’s data, that client’s identity, and a hard ceiling on what it can spend. It answers on an OpenAI-compatible endpoint from the moment it boots, so integrating it was a base URL, the same as pointing at any model API.
> Boon provisions an agent for a client with one API call. Each agent has its own client data and identity, along with a spending limit. It exposes an OpenAI-compatible endpoint, so Boon can connect to it by configuring a base URL.
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
We did some detailed pricing analysis here https://www.agent37.com/pricing#sources
For storage you can request more storage if your use case needs it. And yes would appreciate it if you can include us.
I view it as a wedge to gain market share and later compete on something else.
PS - This is why I loathe advice from prominent software co operators. It's not one size fits all. Uber's strategy is going to be very different than Tesla's strategy which is going to be very different from Amazon's strategy.
Easy to compete+huge margins -> lots of competitors who compete on price -> commotidization -> lower margins -> not good
i think the sandbox part is getting commoditized, like others said. the harder part is what the agent can touch inside it.
you connect google, the agent gets access to everything. sandbox protects the host. it does not protect your tokens.
scoped, short lived credentials per task. that i would pay more for. is it on your roadmap?
It is like a locally-hosted version of these commercial projects. But I'm doing it ad-hoc. This seems like a space that should be filled by open source. What are the options that exist now? I have pro plans for both Codex and Claude Code and enough credits to run a couple instances of each. I want to control them from the mac mini over a tailnet. What options exists now?
https://github.com/smol-machines/smolvm
Docker with tailnet is probably good enough for your usecase.
But there are many tiny details to the whole setup. Like, making sure services start at boot instead of login. And adding isolation to dev resources (I mostly use Postgres and Redis) to avoid agents stepping on each other. There's also things like setting up GitHub Apps so that attribution works well. And then there are the "remote control" features of Claude vs. a persistent tmux I can ssh into. I've could go on, but I think most people will get the point.
I'm actually surprised I don't see more discussion about this from devs.
I recommend "byre" from that list, because I built it. You can inject credentials you want into it, but it can't touch the host. I run all my coding harnesses inside it. At the end of the day, it's a flexible and reusable way of spinning up Docker containers designed for agents.
On a quick skim you have categories: Local, vendor-managed, Hybrid. I am looking for something in-between local and vendor-managed. In a sense, I want the separate box to be the sandbox, rather than have a sandbox on my local machine isolated using a container or VM. That is a bit different of a setup with its own constraints that things like VMs or containers don't directly address.
Does it have a layer that intercepts Cronjob creation, and setups up a reminder on the supervisor to wake the VM to run the agent job?
Cron jobs were a big problem, especially if you want agents that must auto-sleep to save on costs. Since you cannot put the cron jobs within the sandbox container anymore, we eventually created our own cron API to wake up the sandbox and execute the cron
https://www.agent37.com/docs/agents-api/crons#crons
My use case was to play around with hermes. I was using it for a while but I didn’t like how it ended up (the whole set up became overran with files and was a mess, my fault).
I still haven’t 100% figured out how I may want to use the service again, but I thought it was super easy to set up.
My only feedback is that some connectors for google’s integration were kind of privacy nightmare the last time I checked.
Google’s API for using AI has abominable UI and set up.
It would be nice to be able to bridge the gap of simplifying Google’s AI/Service integration while not having to hand over access to every Google service I use.
For connectors we do offer managed MCPs like Composio, BraveSearch, and even an LLM gateway (which routes to openrouter). So what we have is simply a pass through for now and we're not looking to do more there. Since most of our early customers were just launching personal agents like Hermes, OpenClaw, Claude Code and wanted an easy white label setup.
Although now it's expanded to just sandbox usecases.
Yeah in addition to sandbox we also have managed MCPs and our own LLM gateway to make building hosting agent harnesses easier. Most of our customers host hermes, opencode, claude code etc. and needed an easier setup so we ended up offering our own LLM gateway for it, ready to use with the sandbox
> I still can’t retrieve the page from the link: the public-web reader is out of quota, and my direct fetch isn’t available in this session.
I wanted the QM agent to read my website but it says I'm out of quota. Seems a bit odd to have a quota on that. Plan usage explains that there is a quota on searches, which makes sense, but it does not mention that there is one on fetching URLs directly.
edit: Tried again but with Hermes agent and it worked. It was my first time using QM so maybe it's a capability I had to configure.
And so for that it needs workspace credits so that it can spawn new sandboxes for such tasks. Especially if you just started with the free agent.
> When you look at agent harnesses, ... CPU/RAM utilization we could lower the cost.
How does it work today? Is the harness (assuming it means the agentic loop) located in a separate VM and each loop-run invokes a separate sandboxing VM?
For convenience and cross-harness unified API we also built open source Gateway API - https://github.com/agent37-platform/gateway
Think of it as open router for Agent harnesses. So in our default templates we also run this and expose the APIs. So that makes using any harness easy as they all speak a single OpenAI responses API schema.
How would you compare what you do to fly.io's Sprites (which is currently atop my To Try list)?
Fly certainly has great branding since they've been around for a while now. So they have a distribution advantage. But I think at some point they will also need to own some niche rather than just being a generic sandbox company, given how competitive the space is.
YC batch are becoming more like hunger games.
I know a few companies where this is just a feature like digitalocean it is just a feature.
Once there is a winner, there will be a price correction.
In your case, positioning yourself as a cheap provider is inherently a bad idea.
The switching cost is not trivial unlike LLMs
Only if there is some form of lock in or the others go out of business. Both of those are low probability. I'd put a friendly wager on the (lack of) increase of token costs in the next 2 years.
And from what I can tell as you bump more RAM, agent37 is around 5x cheaper: our 2 vCPU / 4 GB box is $4.94/mo (2/4/6 GB disk), vs AWS t4g.medium (the actual 2 vCPU / 4 GB Graviton box) at ~$24.50/mo
There is another even cheaper sandbox which is in YC (boat.dev)
How do you compare to them and how are you cheaper then they are?
Yeah, this seems like a niche where multiple startups are coming in. But if I remember correctly, we're about 3X cheaper than boat. We did a detailed comparison of all sandbox companies and where we stand across vendors here
https://www.agent37.com/pricing#sources