HN Explorer

Show HN: Maritime, a platform for running AI agents for $1 a month (maritime.sh)

2 points by mariagorskikh1 ↗ HN
Hi HN, my name is Maria, and I’m a co-founder of Maritime. We started Maritime at MIT to build infrastructure for companies that need to run thousands of isolated AI agents for their customers.

Imagine you set up an agent like OpenClaw, or a personal assistant agent with a custom framework, and want to give a separate version of it to every customer/friend. Each customer needs their own agent running in an isolated microVM, with persistent state, secrets, triggers, and sleep/wake behavior.

Building such scalable and secure infra will take you months and will cost hundreds of thousands. Also, you still can't vibe code the infra well.

So Maritime handles that infrastructure for you.

We charge $1 per agent per month, so running 100 isolated agents costs $100 a month.

Maritime is designed for companies running thousands of agents, but starting today, any developer can run three agents for free forever.

You can use our templates to spin up OpenClaw, Hermes, and the DeepSeek agent and keep all three for free. You can also deploy custom agents through our CLI or SDK and use Maritime as the infra provider for your stratup.

You can try it at https://maritime.sh. We’d really appreciate your feedback, especially on the developer experience

10 comments

[ 0.36 ms ] story [ 15.3 ms ] thread
abigdog
Compelling pricing compared to exe.dev etc. Because this is Lambdaesque.

How to you avoid the problem of someone 24/7 ing an agent at max CPU and RAM (you would lose money).

Also can you talk to backup/recovery and what happens if you pivot away. I guess main thing is ability to do a takeout from SSD so can use a different host.

Might take free tier for spin.

mariagorskikh1
Free and standard agents automatically sleep when idle and have usage limits, so you can’t run max CPU and RAM 24/7 for $1. Agents have persistent storage with snapshots for backup and recovery. We also don’t want to lock anyone in. You can export your files and data anytime Would love for you to try the free tier!
atmanactive
Where does the LLM run?
mirajane12
Wherever you want - we don't host LLMs, just harnesses
mandarinclips
I registered an account and used it. The whole process was very smooth, and the features are well-designed. I have a question: which company's agent does the Hermes instance use by default? What is the free user quota? Can free users really get a free ride? How do you cover your costs then? I'm concerned about this.
mariagorskikh1
Thanks for trying! The Hermes template uses the open-source Hermes Agent by Nous Research. You can connect your own model provider and API key. The free tier includes up to 3 agents. We cover the infrastructure, but users pay for their own LLM usage after the initial $5 credit expires. Since agents sleep when idle and only consume compute while running, the cost of maintaining inactive agents is extremely low. Paid customers running agents at scale subsidize the free developer tier.
ethannam9022
Why do I get this error when I scroll?

Application error: a client-side exception has occurred while loading maritime.sh (see the browser console for more information).

mariagorskikh1
Did your browser try to auto translate the page? Just fixed that bug thanks for insight
cunjieliu
When I was deploying the agent, I encountered this error

”Backend unavailable“

mirajane12
Hi! Can you try again? Sorry we were overwhelmed with traffic