Hermes Deployment
Create an independent Hermes container instance for each Application. By default, a base image with a fixed release version is used, retaining native functionality; the platform provides purchase, renewal, persistent storage, and deployment management.
¶ Creation and Purchase
- Open Hermes Deployment and create an Application.
- Select a duration package on the purchase page and complete the payment.
- Return to the configuration page, where you can select a platform chat model from the dropdown list and view the current model price. The platform will create independent API credentials for this instance; you can also disable platform access and configure it yourself in the native console.
- Choose to automatically generate access credentials, or set your own strong password/Token; select A2A and EnvarPay as needed, then confirm to begin deployment. Access credentials and model API credentials are independent of each other.
- After the instance is ready, obtain the access address and login credentials from the management page.
- Log in to the native console to configure channels. If platform model access was disabled during deployment, you must also configure the model provider and credentials yourself before chat can be used.
Deployment fees are charged according to the package duration; the specific USD price and duration are subject to the purchase page. Model invocation fees are charged separately; purchasing deployment duration does not include model credits. When platform access is enabled, the dedicated API credentials expose only the chat interface corresponding to the selected model, and usage is charged separately from your platform balance. Each Application is purchased, renewed, and managed separately.
¶ Passwords, Credentials, and Subsequent Configuration
Access credentials are set before the first startup. The automatically generated method uses random credentials, custom passwords must be at least 16 characters, and OpenClaw Tokens must be at least 32 characters. Drafts do not save passwords; you may need to re-enter them after switching pages. After deployment, only the Application owner and administrators can view the access credentials.
The model API credentials for each instance are not reused, their validity is extended with deployment renewal, and they are revoked when the instance is deleted. If the platform model was not connected during the initial deployment, you can select a platform model on that Application's configuration page and redeploy; the platform will update the default model while retaining conversations and other native settings. After that, modify models and channels in the native console; if you switch to a model from another service, first adjust the corresponding interface authorization in platform credential management, or use the corresponding credentials. Ordinary redeployment will not overwrite native settings. Deployment environments that have not passed release verification will temporarily reject new deployments; please contact support.
Model credentials permanently revoked due to security handling will not be restored upon renewal, nor reused during redeployment. If the instance is in a security recovery period, the platform may suspend model access or prohibit the re-enablement of disabled payment components; please contact support to complete recovery at that time. The console being accessible and the Agent showing as online does not mean model invocation has been restored.
¶ Optional Deployment Components
After selecting A2A, the deployment template will start the native Hermes A2A gateway and provide an owner token on the management page. Selecting EnvarPay will additionally install an independent service container and persistent ledger, and requires A2A to be enabled first. EnvarPay initially has only owner access credentials, with no service or payment collection identity, and will not automatically charge fees or make purchases on behalf of users. Neither option will automatically register the instance with Envar; existing instances can enter configuration from the management page and redeploy after enabling them. Enabled components cannot currently be disabled in this wizard.
After A2A is enabled and the instance is ready, the access address card on the management page will display a copyable Agent Card address. Native Hermes A2A uses an independent public address; the Dashboard login address cannot be used as an Agent Card address. If EnvarPay is enabled at the same time, the management page will also display the corresponding "Envar Access Address"; when connecting services to Envar, copy this URL first.
¶ Versions and Data
The configuration page displays the currently released image version. New instances use the currently released service version; existing instances will not be automatically replaced when the catalog is updated. Redeployment will apply the current service version; please back up first and confirm the upgrade requirements of the version in use.
Each instance provides 1 CPU, a 2 GiB memory limit, and 10 GiB of persistent storage by default. Instance data is retained after restart. Actively deleting a deployment or reclamation upon expiration will delete storage; please export any data that needs to be retained in advance.
¶ Renewal and Expiration
Renew on the purchase page of the current Application, and the validity period will be extended according to the platform's existing duration rules. After expiration, the access entry is suspended, and renewing during the grace period restores access; after the grace period, the instance and data will be reclaimed. Refer to the expiration time, billing status, and deletion notice on the management page.
¶ Logging In to the Management Interface
Copy the Dashboard address, username admin, and password from the deployment management page, then open it and log in. Login information is provided only to the owner of that Application and platform administrators. Models, skills, and channels are configured in the native Hermes interface.
¶ Frequently Asked Questions
- Why can't the new instance respond yet? Deployment completion only means that the container is ready. If platform model access was disabled during deployment, select a platform model on the configuration page and redeploy, or configure the model and credentials yourself in the native interface.
- Are additional plugins preinstalled? None are added by default; you can configure them in the management interface as needed.
- How do I update an existing instance? The original Application and order are retained, and the current service version is used during redeployment; back up data and check version compatibility before upgrading.
- What should I do if startup fails? First check deployment logs and events, and configure the model after confirming that the instance is ready. Do not expose instance passwords and keys in public comments or screenshots.