Choosing the right instance size helps your Managed AI Agent run smoothly and provides enough resources for the tasks and workflows it needs to handle.
An instance is the cloud environment where your AI agent runs. The instance size determines the amount of resources available to the agent, including CPU, memory, storage, and bandwidth.
Larger instance sizes provide more resources for agents that handle heavier workloads or multiple activities at the same time.
When choosing an instance size, consider how you plan to use your agent rather than only the size of your business or team.
Important factors include the number and complexity of workflows, how many tasks may run at the same time, connected communication channels, and how frequently the agent is used.
Cloudways Managed AI Agents currently provide four instance tiers: Scout, Operator, Squad, and Swarm. You can select the tier that best matches the expected workload of your agent.
Note:
Resource requirements can vary between Managed AI Agents, such as OpenClaw and Hermes, because each agent may handle tasks, workflows, and concurrent activity differently. Consider the requirements of the agent you select when choosing an instance size.
Instance Size Options
Cloudways provides different instance tiers for Managed AI Agents based on available CPU, memory, storage, and bandwidth.
CPU provides processing capacity, memory helps the agent handle active tasks, and storage is used for the agent's data, files, logs, and other resources.
Your workload should determine which tier you choose. A simple agent used occasionally may require fewer resources, while an agent handling multiple workflows, channels, or concurrent tasks may need a larger instance.
Cloudways currently offers the following Managed AI Agent tiers: Scout, Operator, Squad, and Swarm.
Scout
Scout includes 1 vCPU, 2 GB RAM, and 50 GB storage. Cloudways currently positions it as the entry-level Managed AI Agent tier.
Scout is suitable for simple or low-activity agent workloads, such as:
Testing and learning.
Early prototypes.
Personal AI assistants.
Simple scheduled tasks.
Lightweight workflows that run occasionally.
A prototype is an early version of your agent setup that you use to test an idea or workflow before using it for production.
Scout is a good starting point when the agent performs a limited number of lightweight tasks and does not need to handle significant activity at the same time.
For live or customer-facing workloads where activity may increase unexpectedly, consider a larger instance.
Operator
Operator includes 2 vCPU, 4 GB RAM, and 80 GB storage.
Operator is a practical starting point for a Managed AI Agent that is being used for regular production workloads rather than testing alone.
A production workload means the agent is being used for real tasks, users, or business operations.
Consider Operator when your agent:
Performs regular workflows throughout the day.
Handles moderate activity.
Connects to a communication channel.
Supports an internal assistant or controlled customer-facing workflow.
Needs more resources than a basic testing environment.
For many first-time production deployments, Operator provides a balanced starting point between resource availability and workload requirements.
Squad
Squad includes 4 vCPU, 8 GB RAM, and 160 GB storage.
Squad is suitable for Managed AI Agents that need to handle multiple workflows or tasks at the same time.
Consider Squad when your agent:
Runs several workflows throughout the day.
Connects with multiple communication channels.
Performs multiple tasks concurrently.
Supports customer service, content, operational, or automation workflows.
Experiences regular or increasing activity.
Concurrency means multiple tasks or workflows are active at the same time. Higher concurrency generally requires more CPU and memory resources.
Swarm
Swarm includes 8 vCPU, 16 GB RAM, and 320 GB storage.
Swarm is designed for larger or high-activity Managed AI Agent workloads.
Consider Swarm when your agent:
Handles high levels of concurrent activity.
Runs multiple complex workflows.
Supports busy production environments.
Requires significantly more processing and memory resources.
Is part of a larger automation or agency workflow.
For very large workloads or environments serving separate projects or clients, you may also want to use separate Managed AI Agent instances.
This can help keep resources, configurations, and workloads isolated from each other.
Quick Decision Guide
Use the following guidance to choose your instance size:
Use Case | Recommended Tier |
Prototype, testing, or learning environment | Scout |
One simple agent with low activity | Scout |
Live customer-facing channel with unpredictable activity | Operator or higher |
1 to 2 sub-agents active at the same time | Operator |
3 to 5 sub-agents active at the same time | Squad |
More than 5 sub-agents active at the same time | Swarm |
Agency or high-concurrency setup | Swarm or separate instances |
As a simple rule, Scout is best for learning and testing. Operator is the safest default for most first-time production users.
Squad is better when multiple workflows run during the day. Swarm is best for larger and busier setups.
Signs You Have Outgrown Your Current Tier
You may need a larger instance size if your Managed AI Agent setup starts showing performance issues during normal or peak activity.
One sign is that the Managed AI Agent container restarts unexpectedly during busy periods.
This may happen when the instance does not have enough memory to handle the active workload.
Another sign is that workflows take longer to complete even though you have not changed the workflow itself.
This can indicate that the instance is under pressure because too many tasks are running or the workload has grown.
You may also notice that the Managed AI Agent dashboard feels slow while sub-agents are running.
If the dashboard becomes sluggish during active workflows, the current tier may not have enough resources for your usage pattern.
If these signs appear often, you may have outgrown your selected tier.
What the Instance Tier Does Not Affect
The instance tier affects the resources available to your Managed AI Agent installation, but it does not affect every part of your setup.
It does not affect your LLM costs. LLM costs are billed separately by your AI model provider.
An LLM, or Large Language Model, is the AI model used by your agent to understand and generate responses.
The instance tier also does not affect the region or latency choice. Region selection is handled separately when you launch the instance. Latency means the time it takes for data to travel between the user, the server, and connected services.
The instance tier also does not change feature availability. All tiers include access to supported Managed AI Agent features such as SSH, backups, channel integrations, and BYOK.
BYOK means Bring Your Own Key, which allows you to use your own API key for supported AI providers.
Planning Your Starting Tier
Because resizing is not available during Public Preview, you should choose your starting tier carefully.
Think about how many sub-agents you plan to create and how many of them may run at the same time during your busiest period.
If your agent will only be used for testing or simple scheduled tasks, Scout may be enough.
If your agent will support real users or connect to live channels, Operator is usually a better starting point.
If your workflows are expected to run frequently throughout the day, Squad may be more suitable.
If you expect high activity, many sub-agents, or agency-level usage, Swarm may be the better option.
When you are unsure between two tiers, choose the higher tier. This helps reduce the chance of performance issues after launch and avoids the need to create a new instance sooner than expected.
Important:
Disk space cannot be increased through vertical scaling. Therefore, review your expected storage requirements carefully and select an instance tier that provides sufficient disk space for your OpenClaw data, files, logs, and future usage. If you expect your storage requirements to grow, choose a higher tier when launching the instance.
Conclusion
The right Managed AI Agent instance size depends mainly on concurrency, which means how many sub-agents run at the same time.
Scout is suitable for simple testing and learning. Operator is the recommended default for most first-time production setups.
Squad is better for multiple workflows running during the day. Swarm is suitable for high-concurrency workloads and larger installations.
Choose your tier based on your expected active workload, not only the number of sub-agents you plan to create.
Since resizing is not currently available during Public Preview, plan ahead and select a tier that can support your expected usage.
That’s it! We hope this article was helpful.