Hacker News: vishnukool

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 03:09:38 +0000

Depends on the contract value, let's have a chat https://cal.com/vishnukool/30min

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 03:08:43 +0000

I answered this in detail in another comment above, but really the basics are skip the hyperscalers and place the pods more efficiently based on available resources.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 03:07:24 +0000

Thank you, looking forward to it.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 03:06:14 +0000

Thank you! Omg you're right, I absolutely hate Claude's writing. I get so annoyed even with it's responses as I'm coding.

That's interesting though about Luna. I didn't realize GPT models are so much better at writing. I'll be taking another pass at these!

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 03:02:55 +0000

Thank you! That's great to hear :)

We have a few different types of sandboxes now. The default one's are optimized for cost so the cold start times are higher. But we're also launching performance and full VM which has better metrics on the other factors.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 03:00:40 +0000

Yes, the main factors are exactly the one's i've listed above. For example by skipping the hyperscalers where you get your bare metal you get the biggest bang for buck in cost. AWS has 80-90% margins, so you gotta rent the bare metal directly.

The second big lever is being able to place the pods on hosts with enough CPU/RAM capacity as they awake. Agentic workflows are spiky which means not everyone is going to use all of the cores and RAM all the time, which allows you to play with the placement, and then there's some minor optimizations you can do as you dive deeper.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 02:11:01 +0000

That's fair, capabilities wise we have to limit certain things on what gvisor based sandboxes can do in terms of things like networking, and other capabilities to compensate for this class if sandbox. However over 80% of the use cases I'm seeing simply doesn't need much beyond that.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 00:49:43 +0000

looking forward to it, DM me any feedback on the website chat as you use it :)

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 00:49:09 +0000

We do use cloudflare for networking. But Cloudflare sandboxes are even more expensive than most. It's about 30X lower cost than cloudflare sandboxes.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 00:48:10 +0000

haha, it's been on list for a while, but none of our customers have asked for it so far. But it's easy to build a custom Docker image with that harness and start using it.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Tue, 13 Oct 2026 00:47:21 +0000

yes :)

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 21:44:31 +0000

Interesting, I looked into this. So The t4g.nano is 2 vCPU but only 0.5 GB RAM, so there's that trade off.

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

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 21:36:50 +0000

Great question!

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

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 21:35:40 +0000

haha, the inevitable cycle of capitalism.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 19:54:41 +0000

It's the latter for us. We have healthy margins even at this price point. So we don't actually need a lot of money to do this against incumbents.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 19:19:35 +0000

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

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 19:17:47 +0000

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.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 19:09:54 +0000

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.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 19:06:43 +0000

thank you, yeah we still have a lot to figure out.

New comment by vishnukool in "Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents"

vishnukool — Mon, 12 Oct 2026 18:49:59 +0000

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.