# We run stateful AI agents on a serverless infra

> Source: <https://maritime.sh>
> Published: 2026-08-27 01:04:50+00:00

# Run a thousand agents as easily as one.

Run thousands of customer-facing AI agents on Maritime with isolated microVMs, effortless scaling, and fully managed infrastructure.

Developers building on Maritime work at these companies

## One agent per customer.

Provisioned from your backend.

Every signup gets its own agent. One API call brings up a dedicated micro-VM: tagged with your IDs, holding its own secrets, sending you lifecycle webhooks.

No shared workers. No customer data in another customer's VM.

[Read the build docs](/docs/build)

Not a shared runtime. A micro-VM per agent.

## Isolation your customers can be told about.

## The only platform designed

to scale to thousands of agents.

## From zero to a running agent in about a minute.

## One platform, from your first agent to the millions you sell.

## Flat pricing. Nothing metered.

7

Free $0 | Starter $20/mo | Growth $100/mo | Scale $500/mo | Enterprise Custom | |
|---|---|---|---|---|---|
Agents included | 3 | 20 | 100 | 500 | Custom |
Extra agent per agent / mo | – | $1.50 | $1.25 | $1.00 | Volume |
Extra RAM per GB / agent / mo, 2 GB included, up to 8 | – | $3 | $2.50 | $2 | Custom |
Extra SSD per 5 GB / agent / mo, 5 GB included, up to 100 | – | $2 | $1.50 | $1 | Custom |
Support | Discord community | Discord community | Private Slack + your rep | Private Slack + your rep | Dedicated |
|

[Get started](/signup?plan=starter)[Get started](/signup?plan=growth)[Get started](/signup?plan=scale)[Talk to us](/contact)Every agent comes with 1 vCPU, 2 GB RAM, and 5 GB SSD, and wakes from sleep in about a second.

## Deploy your first

agent for $1.

Start from a template and ship in about a minute. Scale when you're ready and only pay for what you run.