Launch HN: Maritime (YC F26) – A managed cloud for production AI agents

57 points by ashriv a day ago on hackernews | 53 comments

bitlad | a day ago

How do you compare yourself with https://www.agent37.com/

Also, digitalocean offers this now.

demibabs | a day ago

Better landing page animation, of course.

[OP] ashriv | a day ago

Agent37 is great if you want plain, cheap sandboxes. But you still have to build and manage a lot of the infra to sell agents to customers, we manage the entirety so that you don't think about cloud runtime at all and can focus on other things. We also provide you with ongoing support, an infra partner if you may.

DigitalOcean is focusing on coding agent sessions in the cloud, rather than managing the things necessary to sell long living agents to customers.

bitlad | a day ago

There are a lot of alternatives in the market for this.

[OP] ashriv | a day ago

Most are focused on providing commoditized compute, there's a lot more nuance when building an agent company.

linuxamd64 | a day ago

I dont think there is [1]

It is exactly the same offering.

[1] https://www.digitalocean.com/products/managed-agents

bravura | a day ago

Like what?

bitlad | a day ago

Here a list of harness, sandboxes, paas doing the same [1]

[1] https://debarshibasak.github.io/awesome-paas/

sgtwompwomp | a day ago

Cool :) if I used Maritime to power my agent product, would my end users be able to sign in with their existing AI subs? Or would they have to enter their API key.

[OP] ashriv | a day ago

Up to you, we have support for BYOK, AI subs, or pass-through where you can top up our LLM gateway and we take care of spending caps per user, etc. Whatever fits your use case best. What are you building?

asdev | a day ago

there is no such thing as bringing AI subs, it's against TOS on Claude and OpenAI to use your subscription in third party tools. You have to use API key usage which is extra on top of your subscription

momojo | a day ago

Is it bring your own FS?

[OP] ashriv | a day ago

No. We mount an individual /data volume to every VM that persists, but if you have data that's in S3 or R2 you can hook those up as well.

0x0000F8 | a day ago

Right now I'm using Grains.run -- it has toolbox, x402, custom tools, fs, memory, and more

plus it basically plugs into everything out of the box (ides, sdks, apps, etc), I haven't even broken the free tier for all my loads thrown at it.

It's reliable enough we even use it in production systems.

volkk | a day ago

cool product. right now I just built my own version of this on AWS (which is likely far more expensive, but we have startup credits). I'll definitely check this out one day when the credits end/expire. I will say that startup credits would really help!

side note, this design aesthetic is so cool but now literally every SF AI startup uses it -- I'd almost prefer craigslist style where the information is to the point and direct. i.e how much money/time will this save me and is it secure. the two questions i only care to answer here. i think the aesthetic is meaningless at this point bc of how easy it is to vibe this template out

[OP] ashriv | a day ago

Fair! What did you build on AWS? What was the most time consuming part?

volkk | a day ago

its basically a 24/7 box with claude code on it. I think the most time consuming part was not the box setup, but rather getting my local skills/workflows (that are fairly scattered) into something rebuildable/reusable. And as I work on my box, i realize there are missing dev pieces that I had on my local machine so I always have to keep remembering to update the docker image with the base level CLIs/MCPs/skills that i need. Wasn't too bad, but definitely annoying

cidd | a day ago

Is this similar or using CNCF's agent-substrate open source platform?

[OP] ashriv | a day ago

I think the primary distinction here is we let each agent get its own isolated VM. Agent substrate lets you run many agents on shared workers. Plus we run the whole thing for you :)

binsquare | a day ago

It’s been cool to see the evolution from vms to serverless agents.

I think it’s the right kind of innovation sort of like ec2, serverless functions, and etc in the age of ai

[OP] ashriv | a day ago

Thank you! I think this is where things are headed too

ATechGuy2 | a day ago

Congrats on launching! I think the lifecycle management and cost-optimization layers you're building on top of microVMs address some painful problems for teams deploying agents in production.

I work at a neocloud company, and from my experience, getting VMs up and running with Firecracker/KVM on bare-metal infrastructure is relatively straightforward and requires little operational overhead initially.

The real challenge is what comes afterward: continuously monitoring, patching, and responding to newly discovered CVEs. Falling behind on security updates can have serious consequences, and ultimately, it's your customers who bear the risk.

This is one reason I'd be cautious about choosing a smaller provider based solely on price. At the infrastructure level, many providers are essentially selling the same isolated VMs. The real differentiators should be security, reliability, and operational maturity, particularly with AI accelerating vulnerability discovery and expanding the attack surface. Saving a few dollars on compute might not be worth the trade-offs.

There's also the question of geography and latency. If your agents run in a big tech cloud, offloading sandbox execution to infrastructure on another continent isn't necessarily a great choice. The added network latency can significantly impact agent responsiveness, especially when agents need frequent interactions with external services or real-time applications.

[OP] ashriv | a day ago

Thank you! And yes I agree that getting VMs up is quite trivial, patching hosts and guest kernels after CVEs is part of what we mean by "managed" - we don't want our customers having to continuously maintain things.

As for latency, we've noticed that since most agent runs take >10s, a couple extra ms of latency isn't a huge problem for a lot of companies. That said, we're planning on getting more edge hosts, and BYOC.

jeremyjh | 19 hours ago

Did you guys … generate this slop for engagement?

[OP] ashriv | 18 hours ago

Nope

vasco | 15 hours ago

They didn't, they asked their friend to do it for them.

jeremyjh | 10 hours ago

The account is 3 months old and has only posted slop like this on launch threads.

hmokiguess | a day ago

Forgive my naivety, but if it's built for agents then why should humans need to login, view a dashboard, care about it?

Thinking about product market fit, buyer personas, and right audiences here.

Would there be a future where maybe the agent can elevate to the human what the human needs to know when it wants to or requires it from what it has access and these platform-like UX constructs are more like a "just in time" construct similar to Claude Artifacts?

I expect the next cloud for AI to be fully headless, though maybe I'm wrong

[OP] ashriv | a day ago

We are headless! We spent a lot of time fleshing out our CLI so our customers' coding agents can deal with things themselves. That said, a lot of customers want some sort of visual basis to see what's going on, especially if they have a lot of users.

taherchhabra | a day ago

how to provide tools to the agent ? the agent in my product manipulates application state/updates databases etc

[OP] ashriv | a day ago

You'd define the tools in the agent harness, and you can set up env variables through us. You can also connect to on prem databases using things like our connect module.

ianberdin | a day ago

Congratulations on the launch. Very interesting idea. I read your description, and it's striking: it's as if you described our infrastructure at Playcode (https://playcode.io/cloud). The similarity is just colossal, it's what we built for ourselves and for our clients.

samu123123 | a day ago

Its like sandboxes are a popular space or something... who would've thought. its surprising people have similar infrastructure to playcode I truly can't believe it

MisterMunchkin | a day ago

How are you going to pay back the 500k if you’re charging $1/month and competing with a thousand other startups that are all racing towards the bottom?

[OP] ashriv | 20 hours ago

We're not racing to the bottom because sandboxes are a small part of our offering. Every company is going to be running thousands of agents sooner or later, and they'll all need custom environments. More agents = more $

stevelacey | 23 hours ago

I just run Claude Code sessions in tmux on my Mac and talk to them over Telegram. I don't really see what a managed cloud adds for most people.

[OP] ashriv | 23 hours ago

We sell primarily to startups that run agents, rather than directly to individuals. E.g. healthcare agent companies, personal assistants, products with embedded agents, etc.

green-frog-445 | 22 hours ago

sounds like the dropbox comment

[OP] ashriv | 20 hours ago

;)

agent_yard | 21 hours ago

The point about sandboxes being only a small part of the problem makes sense. Lifecycle seems like where most of the custom code ends up. Two questions: how do spend caps work when an agent gets stuck in a loop mid-task, do you stop it hard or let it reach a checkpoint first? And when a VM sleeps and wakes, what state is kept beyond the disk, for example open connections or in-progress tool calls?

[OP] ashriv | 20 hours ago

Spend caps are enforced by us returning a 429 when a model provider is called, you can elect to have some sort of loop detection but that comes down to harness engineering - we don't touch what runs inside of the VM.

In-progress tool calls are kept upon sleep/wake, however, open connections aren't (since typically the other side usually times out either way)

parthg1901 | 13 hours ago

Nice that in-progress tool calls survive sleep/wake. The case I'd worry about is the unplanned one. If a host dies or you roll an update, does the box come back from its last memory snapshot or cold from /data? Coming back from a snapshot means the agent has forgotten whatever it did since, so it can redo a push, a message or a charge that already happened. Since you leave the harness alone, do you at least signal to the VM that it was restored, so the harness can check before repeating a side effect?

jeremyjh | 10 hours ago

More slop from a new account. This launch thread is a joke.

jeremyjh | 10 hours ago

More slop from a new account in this thread.

aqibkhan026 | 20 hours ago

i've been looking into maritime, they're heavily customizable plus it has a really good sdk and interface if you want to integrate it with you existing platform.

[OP] ashriv | 20 hours ago

Thanks!

bill10 | 17 hours ago

A cloud box doesn't really make much sense to me (personal opinion): monthly VM cost + LLM cost is more than a canned personal assistant; or host a agents on a mac mini at home and only pays for the AI subscriptions, which is what I am doing now.

chandureddyvari | 17 hours ago

I might try your platform but I am kind of confused at the pricing.

Let me explain my current setup. We have something like muse/instinct/dots equivalent built for our customers(GTM domain), so each of them gets an agent with a VM (sandbox - currently using daytona). The sessions and the context (skills, instructions, hooks etc.) are synced to R2. Daytona(2GB ram, 3GB disk, 1vcpu) is working out good for us, cold starts are <500ms, whereas warm ones (non-archived sanboxes) are much lesser. Current problems we are facing is around agent swarms or sub-agents or multiple sessions from same customer (teams trying to interact) - we needed to manage the daytona sandbox sizing on this.

If I were to use maritime, what'd be different for me? Would I be paying $1/mo per customer agent? I can just move my harness to maritime and stop managing sandboxes, R2 sync etc.?

Another company I wanted to checkout is Omnara(another YC company), but Maritime felt closer to my task.

fvrshaibu | 16 hours ago

might give it a try, great work

ansh25lehri | 15 hours ago

what kind of cost optimisation support you guys plan to give? Will it be similar to what say AWS offers today at EC2 and other resource levels except you guys on token?

vasco | 15 hours ago

What do you do we don't get with kagent?

jen729w | 15 hours ago

You could stand to hire a copywriter for the product pages. It reeks of being AI generated, and these days that causes me to kinda sigh and not really pay attention. Which might be totally unfair to your product! But it's how I feel.

tobiaszander | 10 hours ago

Permission rules are only half of it. On my own homelab setup, a config linter found 6 MCP server tokens stored in plaintext in ~/.claude.json, even though the permissions were tight. Allowing a whole MCP server also allows its later write tools, and unpinned npx/uvx packages pull the newest version on every start. Wildcards are another trap: Bash(python3:) looks narrow but is effectively Bash(). For agents that change networks or cloud resources, I keep approval gates outside the agent and bind each approval to a specific plan.