Integrations

Configure your favorite AI coding tools — from CLI agents to IDE plugins — to use WisGate models in minutes.

Hermes Agent

A terminal-native autonomous coding agent by Nous Research with persistent memory and multi-backend support.

Hermes Agent

Hermes Agent is a terminal-native autonomous coding agent built by Nous Research. It supports persistent memory, agent-created skills, messaging gateways, and multiple execution backends. You can connect Hermes Agent to WisGate through a custom OpenAI-compatible endpoint.

1. Install Hermes Agent

Follow the official Hermes Agent documentation to install it first. After installation, verify that the command is available:

hermes --version

2. Use the Interactive Model Selector

Hermes recommends configuring models through the interactive selector:

hermes model

During the model setup flow, select a custom OpenAI-compatible endpoint and enter:

  • Base URL: https://api.wisgate.cn/v1
  • API Key: Your WisGate API key
  • Model: For example, gpt-5.5

3. Manual Configuration

Hermes usually stores secrets in ~/.hermes/.env, while model and non-secret settings live in ~/.hermes/config.yaml.

Add this to ~/.hermes/.env:

OPENAI_API_KEY=your_wisgate_api_key
OPENAI_BASE_URL=https://api.wisgate.cn/v1

Configure the model in ~/.hermes/config.yaml:

model:
  provider: custom
  default: gpt-5.5
  base_url: https://api.wisgate.cn/v1

If your Hermes version uses a different field name than model.default, prefer the configuration generated by hermes model.

4. Start Using

hermes

Or use the TUI:

hermes --tui

Use Cases

  • Autonomous development tasks: Let Hermes run multi-step development tasks locally, in Docker, over SSH, or on remote backends.
  • Persistent memory: Preserve project preferences, experience, and skills across sessions.
  • Messaging gateway: Trigger agent workflows from Telegram, Discord, Slack, and other platforms.
  • Auxiliary models: Configure cheaper WisGate models for compression, vision, titles, and other lightweight tasks.

FAQ

Hermes cannot find the API key

Confirm that OPENAI_API_KEY exists in ~/.hermes/.env, then restart Hermes.

Model or context errors occur

Confirm that the model ID is supported by WisGate, and prefer a model with a large enough context window. The OpenAI-compatible Base URL is https://api.wisgate.cn/v1.