Hermes Agent

Hermes Agent is a terminal-based AI agent. With a custom provider, Hermes can use ModelGo's OpenAI-compatible API to call models.

Before you start

Install Node.js 22 or newer.
Create an API key in the ModelGo Console.
Confirm the ModelGo logical model name you want to use in the Model Gallery.

1. Install Hermes Agent

macOS or Linux:

bash

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

Windows PowerShell:

powershell

iex (irm https://hermes-agent.nousresearch.com/install.ps1)

Reopen your terminal and verify the installation:

bash

hermes --version

2. Configure ModelGo

Put your API key in an environment variable for the current shell. Never commit a real key to a repository or public script:

bash

export MODELGO_API_KEY="your-ModelGo-API-key"
export MODELGO_MODEL="your-ModelGo-logical-model-name"

If you are not sure which model name to use, query the models available to the current API key:

bash

curl https://api.modelgo.ai/v1/models \
  -H "Authorization: Bearer $MODELGO_API_KEY"

Use hermes config set to create a custom provider. Replace <model> with a logical model name from the Model Gallery or the GET /v1/models response:

bash

hermes config set model.provider custom
hermes config set model.base_url https://api.modelgo.ai/v1
hermes config set model.api_mode chat_completions
hermes config set model.api_key "$MODELGO_API_KEY"
hermes config set model.default "$MODELGO_MODEL"

If your Hermes version includes the interactive setup wizard, you can run:

bash

hermes model

Choose Custom endpoint, enter the ModelGo Base URL, API key, and model name, and select Chat Completions as the protocol.

3. Check the configuration and start a session

Check the Hermes configuration:

bash

hermes config check

Start Hermes after the check passes:

bash

hermes

Send a message such as “Introduce ModelGo in three sentences.” A model response confirms the connection.

ModelGo values

Setting	Value in ModelGo
Provider	`custom`
Base URL	`https://api.modelgo.ai/v1`
API mode	`chat_completions`
API key	A ModelGo API key created in the Console
Model ID	A ModelGo logical model name, not the upstream provider's raw model ID

Hermes stores non-sensitive settings in ~/.hermes/config.yaml and API keys and other secrets in ~/.hermes/.env. Do not share or commit files under ~/.hermes/ that contain credentials.

Troubleshooting

401 or authentication failed

Make sure the API key is valid and has not been revoked or expired, then run:

bash

hermes config set model.api_key "$MODELGO_API_KEY"

403 or model unavailable

Check that model.default is a ModelGo logical model allowed by the policy attached to your API key.

404 or endpoint not found

Use https://api.modelgo.ai/v1 as the Base URL. Do not append /chat/completions; Hermes adds the request path itself.

Related docs

First call: create an API key, find a model, and verify a ModelGo request.
Authentication: learn how to use and protect ModelGo API keys.
Hermes Agent documentation: see the latest installer, configuration, and CLI reference.