Hermes

Prepare API Access

Have the three items below ready before you configure anything:

API Key

The key string you generated when creating your API Key.

Base URL

https://api.watt-cloud.com/v1

The trailing /v1 is required — do not drop it.

Model Name

Take the complete model identifier from the Model Marketplace, for example DeepSeek-V4-Pro.

Installing Hermes

Installers come from Hermes' official channels — see Installation | Hermes Agent.

Linux / macOS / WSL2

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

There is no native Windows build of Hermes. Set up WSL2 first and run Hermes Agent inside it; the command above is executed within the WSL2 environment.

Android / Termux

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Connect Hermes to Watt Cloud

Edit the Configuration File

Open ~/.hermes/config.yaml and insert or adjust the model block:

model:
  default: GLM-5.1
  provider: custom
  base_url: https://api.watt-cloud.com/v1
  api_key: your-api-key
  context_length: 200000
  max_tokens: 200000

Field Reference

Field	Description
default	Model used by default, such as GLM-5.1, DeepSeek-V4-Pro, or MiniMax-M2.7
provider	Must be custom when a custom API is being connected
base_url	The API endpoint; keep the trailing /v1
api_key	The API Key string you created
context_length	Size of the context window
max_tokens	Upper limit on output tokens

Change the Model

Swapping in a different model only requires editing default:

model:
  default: DeepSeek-V4-Pro
  provider: custom
  base_url: https://api.watt-cloud.com/v1
  api_key: your-api-key
  context_length: 200000
  max_tokens: 200000

Applying the Changes

Once the file is saved, a restart applies the new configuration:

hermes gateway restart