Agent37 (YC F26) 发布低成本 AI Agent 沙箱服务，成本降至主流厂商 10% 以下

Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents 50 points by vishnukool2 hours ago | hide | past | favorite | 36 comments 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 help alasano1 hour ago | next[–] 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 reply vishnukool1 hour ago | parent | next[–] Boat is a great company too! As far as pricing goes our default sandboxes are about 2.8X cheaper than boat. 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. reply mparis1 hour ago | prev | next[–] 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! reply vishnukool42 minutes ago | parent | next[–] Thank you ! And agreed, it's an extremely competitive space. In our YC batch alone there's probably 5+ companies doing something similar. Interestingly enough though atleast for now we're all rapidly growing, so that's promising. But eventually I see us all moving in slightly different spaces as we specialize. reply mparis23 minutes ago | root | parent | next[–] Great to hear you are growing! Take this as you might grains of salt. 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! reply vishnukool19 minutes ago | root | parent | next[–] thank you, yeah we still have a lot to figure out. reply stillpointlab19 minutes ago | prev | next[–] Tangentially, I've been investigating the last few days on how to setup a separate Linux box as an agent "playground". I got a mac mini to use as my own personal driver and now my Linux box is free, so I want to have a local setup where I keep my personal machine a bit stricter while giving near free-reign for agents on the Linux machine. 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? reply vishnukool8 minutes ago | parent | next[–] Agent Substrate from google if you wanna go hardcore, although it adds quite a bit of complexity and management that you probably don't want if it's just a personal setup - https://github.com/agent-substrate/substrate Docker with tailnet is probably good enough for your usecase. reply MikhailTal56 minutes ago | prev | next[–] 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 reply vishnukool51 minutes ago | parent | next[–] There's a talk from Travis Kalanick recently on a podcast about this. It talks about the advantages of a startup vs an incumbent. My read is if a startup competes on price, the incumbent has no choice but to first let them gain a bunch of market share. It's too expensive for the incumbents to compete on price because a no-name startup is doing it. So they'd have to let you get relevant enough for it to make sense to compete on that axis. I view it as a wedge to gain market share and later compete on something else. reply rajangdavis1 hour ago | prev | next[–] I have been using your service for a few months… super easy to set up and use. I signed up after my bank would not let me process a payment to Hetzner :) 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. reply vishnukool1 hour ago | parent | next[–] Thank you, that's so great to hear ! 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. reply olalonde1 hour ago | prev | next[–] Pretty cool, trying it out. What LLM is it using in the free tier? I was surprised that it worked without supplying an API key. The model doesn't seem to know either: "This run is labeled agent37/default. That’s the configured model name I can see; it doesn’t reveal which underlying model/provider it maps to.". reply vishnukool1 hour ago | parent | next[–] We use OpenAI Luna for the agent37/default model for that. 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 reply olalonde48 minutes ago | root | parent | next[–] Also, curious if this is intended or a bug: > 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. reply vishnukool16 minutes ago | root | parent | next[–] So the QM agent is a bit different than a typical harness. It sometimes for tasks that it needs to do more research, launches a separate sandbox per user where it does all the hard tasks. 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. reply ATechGuy21 hour ago | prev | next[–] This is cool; pricing is certainly appealing. At the same time, there are a ton of sandboxing providers. > 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? reply vishnukool38 minutes ago | parent | next[–] That's right each harness runs in it's own sandbox. Really the harness itself is just a docker template with some pre-installed harness (say openclaw, hermes, claude code, opencode, pi, grok etc) that runs. 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. reply pranshuchittora20 minutes ago | prev | next[–] Just use EC2 t4g.nano reply christoff121 hour ago | prev | next[–] I have yet to use sandboxes though have some experimentation planned for a new gig I'm starting in a week. How would you compare what you do to fly.io's Sprites (which is currently atop my To Try list)? reply vishnukool55 minutes ago | parent | next[–] Similar to Sprites in capability, so if you can use sprites you can use agent37. We're also about 94% lower cost than them. 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. reply bitlad1 hour ago | prev | next[–] I had ran into another yc startup from the same batch doing the same thing recently. I think it was called maritime. 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. reply calebkaiser1 hour ago | parent | next[–] I'd be curious to see stats on overlap among startups by batch historically. My impression is that this has always been a thing. Based on where the market/technology horizon currently is, there are some buckets that are very "startup shaped". Founders who are iterating on ideas using similar criteria will often end up in the same proximity, especially in an accelerator environment. But it would be extremely interesting to see if this has become more prevalent over time, or at least since the explosion in the AI market. reply bitlad1 hour ago | root | parent | next[–] It is also funny to see folks and friends of the startup commenting and trying to boost this post which is against the guidelines, but thats ok. reply vishnukool36 minutes ago | parent | prev | next[–] hahaha, I suppose it is becoming a bit like hunger games, haha. I was genuinely surprised to see how much overlap there was in the batch across startups. reply risyachka1 hour ago | parent | prev | next[–] Yeah its a race to the bottom as ai can vibe code any infra now reply vishnukool1 hour ago | root | parent | next[–] hahaha, I think it's the same thing as what's happening with LLMs and token cost. reply bitlad1 hour ago | root | parent | next[–] Bruh, that's lack of understanding and insight as well as naivety. It is not a race to the bottom. LLM is the winner-takes-all market. Competitors are pricing against each other to come out on top. 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. reply vishnukool7 minutes ago | root | parent | next[–] This hasn't happened in the sandbox space though. For example Modal was early to it, and yet you see Daytona, E2b and many others doing quite well. The switching cost is not trivial unlike LLMs reply jpadkins1 hour ago | root | parent | prev | next[–] > Once there is a winner, there will be a price correction. 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. reply invalidOrTaken1 hour ago | prev | next[–] This is freaking great. Thank you for posting! reply vishnukool1 hour ago | parent | next[–] glad to hear it, thank you! reply colesantiago1 hour ago | prev[–] Hi, Vishnu, congrats on the launch. 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? reply vishnukool1 hour ago | parent | next[–] Thank you! 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 reply nlpnerd1 hour ago | parent | prev | next[–] What about Maritime.sh (which is also in YC)? I swear everybody in SF is building the same stuff. Lol reply alasano1 hour ago | parent | prev[–] Funny I just asked that too but in my quick check boat was slightly more expensive albeit with more storage space. reply Consider applying for YC's Winter 2027 batch! Applications are open till November 2. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: