Hermes

Use this for OpenAI groups such as Codex Plus Pool and Codex Pro Pool.

Install Hermes

Hermes runs locally from your terminal.

Windows users should use WSL. macOS and Linux users can install it directly from the terminal.

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

Restart your terminal after installation.

Configure Hermes

Open the Hermes config directory:

cd ~/.hermes

Edit config.yaml:

model:
  provider: custom
  default: gpt-6-astra
  base_url: https://codex-everywhere.com/v1
  api_mode: chat_completions

Edit .env and enter your CE API key:

OPENAI_API_KEY=your-ce-api-key

Use an API key from an OpenAI-compatible CE group, such as Codex Plus Pool or Codex Pro Pool.

Caching

Caching is optimized for Codex and OpenCode. Hermes may experience lower cache hit rates, so test cache behavior with your own workload.

Start Hermes

hermes

If Hermes returns a normal response, your configuration is working.