Client integrationsBeginnersUpdated

Set up Hermes Agent

The example uses Kimi K3.1 Pro (k3.1-pro). Get an I Code Easy API key from API keys.

Installation

Run this command on Linux, macOS, or WSL. For native Windows, follow the PowerShell steps in the official installation guide.

bash
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

Hermes Agent

This configuration sends Chat Completions requests to /v1/chat/completions.

Merge the configuration into ~/.hermes/config.yaml. On native Windows, the default directory is %LOCALAPPDATA%\hermes. If you set HERMES_HOME, use that directory.

yaml
providers:
  icodeeasy:
    api: https://api.icodeeasy.cc/v1
    key_env: ICODEEASY_API_KEY
    transport: chat_completions
model:
  default: k3.1-pro
  provider: custom:icodeeasy

Add this line to .env in the same directory and replace YOUR_API_KEY with your key.

dotenv
ICODEEASY_API_KEY=YOUR_API_KEY

Start a session

Run hermes to start a session. To switch in an open session, use /model custom:icodeeasy:k3.1-pro.

Verify your first request

Send a short text prompt and check the model and request status in Usage logs. For a 401 error, check the key. For a model or permission error, check the model ID and selected endpoint. If the connection is unstable, try https://jp.icodeeasy.cc or https://sg.icodeeasy.cc and keep the /v1 path.

Official client documentation