Hermes Agent

Hermes Agent is an open-source terminal AI programming assistant. It supports intelligent conversation and code assistance by allowing the integration of custom models.

Prerequisites

• You have activated a TCB environment and obtained the environment ID cloudBaseEnvID.

• Enable the required model in the AI console.

• Obtain the Base URL and API Key in the AI console.

Configuration Steps

CLI Interactive Wizard

The system guides you through entering the API Key and model name step by step via the command-line interactive menu. This method is recommended for initial configuration.

1. Run the following command in the terminal to start up the configuration wizard.

hermes model

2. Select Custom endpoint (enter URL manually) and fill in the interactive form below according to the table.

Field	Description
API Base URL	The request address for the large model API, which is obtained in the AI console and has the format https://{{cloudBaseEnvID}}.api.tcloudbasegateway.com/v1/ai/cloudbase.
API Key	The key for calling the large model, which is obtained in the AI console.
API compatibility mode	Select "1" Auto-detect
Model Name	The large model identifier. Copy the ID of an enabled model from the model list in the AI console and enter it here, for example, hy3-preview.

3. You can start using it after the configuration is complete.

Manually Modify Configuration File

The core settings of Hermes Agent are stored in the ~/.hermes/config.yaml file. You can directly modify this file to integrate custom models.

1. Open the configuration file.

note

If you use your file browser to locate files, note that the file browser hides files with names starting with a period (.) by default. You may need to enable the hidden files option in your file browser to view them.

On macOS, use the Finder shortcut Command + Shift + . to show hidden files. On Windows, you can select "File Explorer - View - Show - Hidden items". Open.

• Configuration Path for Mac/Linux

~/.hermes/config.yaml

• Configuration Path for Windows

C:\Users\<YourUsername>\.hermes\config.yaml

2. Enter the configuration.

Enter your custom model configuration in config.yaml. The meanings of the fields are as follows:

Field	Description
model.default	The name of the model used by default. Copy the ID of an enabled model from the model list in the AI console and enter it here.
model.provider	The provider type. Enter custom to indicate a custom integration.
model.base_url	The request address (Base URL) for the large model API, which is obtained in the AI console.
model.api_key	The key (API Key) for calling the large model, which is obtained in the AI console.

Configuration example:

model:
  default: hy3-preview
  provider: custom
  base_url: https://{{cloudBaseEnvID}}.api.tcloudbasegateway.com/v1/ai/cloudbase
  api_key: eyJhbGciOiJSUzI1N...

3. You can start using it after the configuration is complete.

Common Error Troubleshooting

Error Message	Solution
404 AI_MODEL_NOT_FOUND	The Base URL is entered incorrectly. Go to the AI console to copy the correct Base URL.
401 Authentication Failed	The API Key is entered incorrectly or may have been deleted.
429 Token usage exceeded quota	An incorrect large model name is configured, or the large model is not enabled in the AI console.