One server. Unlimited agents.
Most managed AI tools charge per agent. You end up paying for three or four separate subscriptions to run specialized agents — a researcher, an operator, a support triage bot.
Hermes OS takes a different approach: you pay for compute, not for agents. Spin up unlimited agent profiles on a single instance. Each profile has its own memory, its own tools, its own personality — and they can coordinate with each other.
On the Fleet plan, agents share a key vault and can hand off tasks between each other. On the Command plan, agent-to-agent coordination is first-class.
- Unlimited agent profiles per instance — no per-agent pricing
- Each agent has isolated memory, tools, and configuration
- Shared AI key vault across all agents on Fleet+
- Agent-to-agent task handoff on Fleet and Command plans
- Manage all agents from a single dashboard
Is there a limit on how many agent profiles I can create?
No. You can create unlimited agent profiles on any Hermes OS plan. The practical limit is your compute pool — vCPU and RAM.
Can different agents use different AI models?
Yes. Each agent profile can be configured with its own model preference. You can have one agent using Claude and another using GPT-4o on the same instance.
What's the difference between Operator and Fleet for multi-agent use?
Both support unlimited profiles. Fleet (8 vCPU, 16 GB RAM) is recommended for running 3+ active agents simultaneously. It also adds shared key vault and agent coordination features.