Hermes Agent

Hermes Agent is an open-source terminal AI agent by Nous Research with tool calling, file I/O and code execution. Its built-in Custom Endpoint support connects to any OpenAI-compatible API — including BeLive Studio.

• Official site: https://hermes-agent.nousresearch.com
• GitHub: https://github.com/NousResearch/hermes-agent

Prerequisites

• Hermes Agent installed
• Base URL: https://api.tokenhub.belivestudios.com
• API Key: create one in "API Tokens" on the BeLive Studio Console
• Model name: exactly matching a model ID in the console model list

Setup

1. Run the interactive model configuration:

hermes model

2. Choose "Custom Endpoint" from the menu
3. Fill in:
   • Base URL: https://api.tokenhub.belivestudios.com
   • API Key: your BeLive Studio API key
   • Model ID: e.g. gpt-5.6-sol
4. Save — no manual file editing needed

Switch models anytime in a conversation with /model.

FAQ

Failed to save the custom endpoint? Check the base URL ends with /v1; Hermes runs a connectivity test and errors if the endpoint is unreachable.

Skill/tool calls misbehaving? Make sure the selected model supports function calling (most mainstream models do).