Hosted Hermes, always on

What it can do

Run code

Executes code in an isolated sandbox and returns the results in chat.

Browse the web

Reads pages and researches live information on request.

Generate media

Creates images, video, and audio with the EmpirioLabs media models.

Use any model

Calls any EmpirioLabs model through your account, on one bill.

Where it lives

Connect the agent to the channels you already use:

Plans

Each agent is its own subscription, billed per deployed agent per month. Model usage is pay as you go on your normal rates.

Hosted Agent Basic

$15/mo per agent$180 $162/yrsave 10%

Managed agent with persistent storage.

• Always-on managed runtime, isolated per account
• 10 GB persistent storage
• Up to 3 agents per account
• Model usage billed separately, pay as you go

Hosted Agent Pro

$30/mo per agent$360 $324/yrsave 10%

More memory and CPU for busy agents.

• Always-on managed runtime, isolated per account
• 20 GB persistent storage
• Up to 3 agents per account
• Model usage billed separately, pay as you go

Common questions

What is a hosted agent?

A managed, always-on AI agent runtime: it keeps its own persistent storage, runs around the clock without your machine being on, and uses EmpirioLabs models through your account so everything lands on one bill.

How much does it cost?

The live per-agent plans are listed on this page, plus pay-as-you-go model usage at your normal EmpirioLabs rates. Annual billing takes 10% off.

Can I switch runtimes later?

Yes. Both managed runtimes deploy in one click from the same dashboard, and you can deploy the other one at any time.

Can I manage agents through the API?

Yes. Agents can be deployed and managed under /v1/hosted-agents on api.empiriolabs.ai as well as from the dashboard. The full reference is in the Hosted Agents docs.