What it does
Maritime · Hosting platform for AI agents
Product and access
Maritime provides the runtime environment; the selected agent framework determines capabilities and tool access.
Core features
5 features from provider sources · checked on 10 October 2026. Availability and limitations follow below.
Persistent storage
The persistent volume is usually mounted at /data and survives restarts and deployments.
Source 2Events wake agents
Messages, platform triggers, web requests and file or exec API calls wake sleeping agents.
Source 2Manage agents programmatically
Dashboard, CLI, REST API and SDKs support provisioning and management.
Source 2Templates and custom containers
An existing agent framework or a custom Docker container supplies the agent logic.
Source 2
Does it fit my task?
Practical tasks
Editorial examples based on documented features. No product tests performed.
Run recurring research
- Your input
- An agent framework, sources and a platform schedule.
- Possible result
- An agent gathers results and saves them to the persistent volume.
- What to check
- Check sources, storage paths, recovery and model costs.
Provision an agent per user
- Your input
- Your own application connected to the Maritime SDK.
- Possible result
- Separate agent instances for application users.
- What to check
- Check permissions, data isolation and concurrently active instances.
An agent gathers results and saves them to the persistent volume.
Your possible prompt
Design a process for new requests: capture information, sort it by topic, and create a proposed response. Plan an approval step before external actions.
Getting-started idea based on documented capabilities. Not an executed product test. Adapt the task, data, and permissions.
Requirements and limits
Limitation
Choose storage paths deliberately
Files outside the persistent volume are disposable.
Source 2Limitation
Configure schedules on the platform
In-process timers do not run during sleep. Recurring tasks need platform triggers.
Source 2Requirement
Account for model access
Model calls use separate AI credits or your own provider keys. Claude Code requires an Anthropic key.
Source 2Not yet confirmed
Test login persistence
Persistence of specific browser logins and recovery after failures have not yet been tested by the editor.
Source 2
Can I use it?
Europe & regional availability
Initial review of the linked product source. European availability of individual features remains to be established.
Reviewed scope: Product overview; not a complete country and feature audit
Reviewed on:
Evidence incomplete
Feature availability still unclear
This profile lacks reliable, feature-specific information for Europe. Before choosing, check country, plan and connected model services with the provider.
Region, reason and source
Region covered: EU/EEA, United Kingdom and Switzerland: to be checked separately
Regulatory reason: not documented
Cost and effort
Prices and included usage
Pricing checked
Free: 3 agents; Starter: USD 20/month. Model usage billed separately.
| Plan | Price | Included |
|---|---|---|
| Free | USD 0 | 3 agents, with 1 awake at a time. |
| Starter | USD 20/month | 20 machines, with 5 awake at a time. |
| Growth | USD 100/month | 100 machines, with 25 awake at a time. |
- Hosting and model usage are billed separately. Larger plans and paid resource upgrades are available.
- Always-on costs an additional USD 20 per machine per month on the listed paid plans.
Setup
Create an account, choose an agent template or your own container and configure model access.
Operation & oversight
Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured.
Deployment covered: Managed Maritime runtime; agent behavior depends on its framework
Sources reviewed:
Documented with conditions
Files and work state
The persistent volume, usually /data, survives restarts and deployments; other paths are disposable.
EvidenceDocumented with conditions
Authentication
Environment variables are stored encrypted. The validity of specific browser logins remains open in this source.
EvidenceDocumented with conditions
Starting further runs
Messages, platform triggers, web requests and file/exec calls wake agents. In-process timers pause during sleep.
EvidenceOpen in reviewed sources
Human intervention
A uniform action approval mechanism across agent frameworks is not established here.
EvidenceOpen in reviewed sources
Recovering from errors
Sleep/wake preserves state. Recovery from arbitrary application errors remains open.
Evidence
Editorial assessment
The managed runtime reduces infrastructure setup. Storage paths, schedules and framework error behavior remain configuration tasks.
Evidence and open questions
Open points
The reviewed sources contain no reliable information on these points. A gap says nothing about the product.
Not yet researched
- Accounts & permissions
Europe: evidence incomplete
Requirements and limits: not yet confirmed
Sources and evidence
Official product documentation reviewed. Workflows and assessments are editorial; hands-on product tests are outside the scope of this directory.
Editorial team: Michael Meierhoff · sources reviewed on . Provider information is not independent evidence of performance.
Provider
Provider of the managed Maritime platform for running agents.
- Operator
- Maritime AI, Inc.
- Organization
- Company
- Website
- maritime.sh