Integrations

Hermes

Install Hermes Agent and connect it to Qubrid AI models through the OpenAI-compatible API

Hermes Agent is an open-source autonomous AI assistant by Nous Research. Connect it to Qubrid AI to use Qubrid models through Hermes's full setup wizard and interact via the CLI or messaging channels such as Telegram, WhatsApp, and Discord.

Prerequisites:

A terminal or PowerShell on your machine (Linux, macOS, WSL2, Termux, or native Windows)
A Qubrid account on the Qubrid AI Platform
A Qubrid API key (how to generate an API key)

Install Hermes

The installer handles everything automatically: uv, Python 3.11, Node.js, ripgrep, ffmpeg, and a portable Git Bash (MinGit on Windows, unpacked to %LOCALAPPDATA%\hermes\git - no admin required, completely isolated from any system Git install). Hermes uses this bundled Git Bash to run shell commands.

If you already have Git installed, the installer detects it and uses that instead. Otherwise a ~45MB MinGit download is all you need - it won't touch or interfere with any system Git.

Run the installer

Open a terminal or PowerShell and run the command for your platform.

Linux, macOS, WSL2, or Termux:

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

Windows (native or PowerShell):

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

Resolve Windows Smart App Control blocks (if needed)

If Windows reports that parts of this app have been blocked during installation, you may need to adjust Smart App Control.

Open Windows Settings → Privacy & security → Windows Security → App & browser control → Smart App Control.
Turn Smart App Control off if it is enabled.

Smart App Control is a Windows security feature. Review the implications carefully and proceed only with your own due diligence. Disabling it may reduce protection against untrusted applications.

Choose full setup

When prompted, Hermes offers two setup modes:

Quick setup
Full setup

Type 2 and press Enter to choose Full setup. This lets you configure every provider, tool, and option yourself, including bringing your own API keys.

Configure Qubrid AI in Hermes

Select Custom Endpoint provider

When asked to select a provider, choose Custom Endpoint (enter URL manually).

Type the number shown next to that option and press Enter.

Enter the Qubrid API base URL

When prompted for the API Base URL, enter:

https://platform.qubrid.com/v1

Press Enter.

Paste your Qubrid API key

When asked for an API key, select the option to paste your key now.

Open the Qubrid AI Platform and create an API key. Follow the steps in How to generate an API Key.
Copy the key and paste it into the prompt, then press Enter.

Your API key is shown only once for security. Store it somewhere safe and secure before closing the dialog. If you lose it, you must generate a new key.

Select Chat Completions compatibility

When prompted for API Compatibility mode, select Chat Completions.

Type 2 and press Enter.

Enter the model name

Enter the model name for the Qubrid model you want to use.

Browse the available models in Serverless Models and copy the API model string for your chosen model. Paste it into the prompt and press Enter.

For example, GPT OSS 120B uses:

openai/gpt-oss-120b

Model strings are case-sensitive and must match exactly.

Set context length and display name

When prompted for context length, leave the field blank to let Hermes auto-populate the value.

When asked for a display name, enter any label you prefer - for example:

Qubrid AI Platform

Select the terminal backend

Hermes asks you to choose a terminal backend. For most users, Local (option 1, the default) works well.

Type 1 and press Enter, or choose another backend if you have a specific need.

Configure or skip messaging platforms

Hermes lists platforms you can connect, such as Telegram, WhatsApp, SMS, Discord, Microsoft Teams, Email, and others.

Configure now - Follow the extra CLI steps to link your account on the platform you choose.
Skip - You can add platforms later and use Hermes from the CLI in the meantime.

Configure or accept default CLI tools

Hermes shows CLI tools that are already selected, such as web search and image generation.

If the defaults work for you, press Enter to continue. Some tools (for example X search) require extra configuration steps - add only the tools you are ready to set up.

Select browser automation provider

When asked for a browser automation provider, select Local browser.

Type 1 and press Enter, or choose another option if you prefer.

Select image generation and TTS providers

Image generation - Select a provider from the list, or choose Skip if you do not need image generation.

Text-to-speech (TTS) - Microsoft Edge TTS is free and a good default, or choose Skip if you do not need TTS.

Select a search provider

Choose a search provider based on your preference, or skip if you do not need web search.

Review the setup summary and launch

Hermes displays a summary of your configuration. Once setup completes, the agent is ready to launch.

Start Hermes

In your terminal or PowerShell, run:

hermes

Press Enter. If you see errors on Windows, Smart App Control may still be blocking parts of the app - review the Smart App Control step above with your own due diligence.

Hermes Agent is now live. Send a test prompt to confirm responses are coming from Qubrid.

Your Qubrid integration with Hermes is now configured. You can chat from the CLI and add messaging platforms whenever you are ready.

Things you can do with Hermes

Once setup is complete, try these examples:

Chat in the CLI - Ask questions, draft content, or debug code using your Qubrid model.
Connect messaging apps - Talk to your assistant on Telegram, WhatsApp, Discord, Microsoft Teams, and other supported channels.
Use built-in tools - Web search, browser automation, image generation, and text-to-speech depending on what you configured.
Switch models - Re-run setup or edit your Hermes configuration to add more Qubrid models.

For more commands and features, see the Hermes Agent documentation.

Monitor usage on Qubrid

Keep an eye on your usage and costs on the Qubrid platform.

Review Inference Logs to see request history and debug issues.
Check your credit balance before long-running or high-volume sessions.
Rotate API keys if you suspect a key was exposed.

Exit and uninstall

Exit Hermes - Press Ctrl+C, then run hermes exit.
Uninstall Hermes - Run hermes uninstall and follow the prompts.

Configuration reference

Use these values when connecting Hermes to Qubrid during full setup:

Setting	Value
Setup mode	Full setup (`2`)
Provider	Custom Endpoint (enter URL manually)
API base URL	`https://platform.qubrid.com/v1`
API Compatibility mode	Chat Completions (`2`)
Example model string	`openai/gpt-oss-120b`
Display name	`Qubrid AI Platform` (or any label you prefer)
Terminal backend	Local (`1`)
API key	Your Qubrid API key

Model strings vary by model - always copy the API model string from Serverless Models.

Frequently Asked Questions (FAQ)

Go to Hermes Agent Docs

If you have any questions related to Hermes Agent, this is your place to be

PreviousCursor NextFine Tuning