Hermes Agent

Quick setup

Run the setup script in a terminal and choose Hermes Agent from its list. It finds Hermes Agent's settings, checks your API key, and makes the changes described below for you, backing up each file first. It can set up your other agents in the same run.

curl -fsSL https://www.greentokens.io/setup.sh | bash

The script saves your key as the GREENTOKENS_API_KEY environment variable, which Hermes Agent reads. Open a new terminal window afterwards so it picks it up.

Set up with the wizard

Hermes Agent works with any OpenAI-compatible API. Run its model wizard from your terminal (not inside a chat session) and choose a custom endpoint:

hermes model
# → Custom endpoint (self-hosted / VLLM / etc.)
# → API base URL:  https://api.greentokens.io/v1
# → API key:       sk-gt-…
# → Model name:    claude-sonnet-5

The wizard saves your answers to Hermes's config file, so they survive restarts.

Or edit the config

The same setup by hand. Keep the key in ~/.hermes/.env and reference it with key_env, so it never sits in the config file:

model:
  provider: custom
  default: claude-sonnet-5
  base_url: https://api.greentokens.io/v1
  key_env: GREENTOKENS_API_KEY

• base_url includes /v1.
• default is any text model ID from the models page.

Switching models

Inside a session, switch to another GreenTokens model with /model custom:model-id, for example /model custom:gpt-6-sol.