Hermes Agent Setup

This guide describes how to configure Hermes Agent to use Aiberm as its model provider. Hermes Agent is an open-source AI agent developed by Nous Research that runs in the terminal and integrates with messaging platforms including Telegram, Discord, Slack, WhatsApp, and Signal.

Because Aiberm exposes an OpenAI-compatible /v1 API, it can be registered as a custom provider in Hermes Agent without installing any plugin or modifying source code. Once configured, a single API key gives you access to all models available on Aiberm, including Claude, GPT, Gemini, DeepSeek, Kimi, MiniMax, GLM, and Grok.

Prerequisites

An Aiberm account (Sign up)
An Aiberm API key (Get your key)
Hermes Agent installed — see the official installation guide

Quick install (Linux / macOS / WSL2):

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

Configure Aiberm as a Provider

Hermes Agent stores its configuration at ~/.hermes/config.yaml. Open the file and add an aiberm entry under the providers: section.

If you’re not comfortable with command-line editors like Vim, you can open the configuration file using your operating system’s built-in editor:

macOS: Open Finder, press Shift + Command + G, enter ~/.hermes in the dialog that appears, and press Return. Locate the config.yaml file, right-click it, and select Open With → TextEdit.

Windows: Open File Explorer, type %USERPROFILE%\.hermes in the address bar, and press Enter. Right-click config.yaml and select Open with → Notepad.

After editing, remember to save the file (Command + S on macOS, Ctrl + S on Windows), then proceed to the restart step described below.

model:
  default: claude-sonnet-4-6
  provider: aiberm

providers:
  aiberm:
    base_url: https://aiberm.com/v1
    api_key: sk-your-aiberm-api-key
    type: openai
    default_model: claude-sonnet-4-6
    models:
      # Claude
      - claude-opus-4-7
      - claude-opus-4-6
      - claude-opus-4-6-thinking
      - claude-opus-4-5-20251101
      - claude-opus-4-5-20251101-thinking
      - claude-sonnet-4-6
      - claude-sonnet-4-6-thinking
      - claude-sonnet-4-5-20250929
      - claude-sonnet-4-5-20250929-thinking
      - claude-haiku-4-5-20251001
      - claude-haiku-4-5-20251001-thinking
      # Claude (anthropic/ prefix)
      - anthropic/claude-opus-4.7
      - anthropic/claude-opus-4.6
      - anthropic/claude-opus-4.6:thinking
      - anthropic/claude-opus-4.5
      - anthropic/claude-opus-4.5:thinking
      - anthropic/claude-opus
      - anthropic/claude-sonnet-4.6
      - anthropic/claude-sonnet-4.6:thinking
      - anthropic/claude-sonnet-4.5
      - anthropic/claude-sonnet-4.5:thinking
      - anthropic/claude-sonnet
      - anthropic/claude-haiku-4.5
      - anthropic/claude-haiku-4.5:thinking
      # GPT / OpenAI
      - gpt-5.4
      - gpt-5.4-xhigh
      - gpt-5.4-mini
      - gpt-5.3-codex
      - gpt-5.3-codex-xhigh
      - gpt-5.2
      - gpt-5.2-chat-latest
      - gpt-5.2-codex
      - gpt-5.1
      - gpt-5.1-codex
      - gpt-5.1-codex-max
      - gpt-5
      - gpt-5-mini
      - gpt-5-nano
      - o3-mini
      - gpt-4.1
      - gpt-4.1-mini
      - gpt-4.1-nano
      - gpt-4o
      - gpt-4o-mini
      # GPT / OpenAI (openai/ prefix)
      - openai/gpt-5.4
      - openai/gpt-5.4-mini
      - openai/gpt-5.3-codex
      - openai/gpt-5.2
      - openai/gpt-5.2-chat
      - openai/gpt-5.2-codex
      - openai/gpt-5.1
      - openai/gpt-5.1-codex
      - openai/gpt-5.1-codex-max
      - openai/gpt-5
      - openai/gpt-5-codex
      - openai/gpt-5-mini
      - openai/gpt-5-nano
      - openai/gpt-4.1
      - openai/gpt-4.1-mini
      - openai/gpt-4.1-nano
      - openai/gpt-4o
      - openai/gpt-4o-mini
      - openai/o3-mini
      # Gemini
      - gemini-3.1-pro-preview
      - gemini-3.1-pro-preview-thinking
      - gemini-3.1-flash-lite-preview
      - gemini-3.1-flash-image-preview
      - gemini-3-pro-preview
      - gemini-3-pro-preview-thinking
      - gemini-3-pro-image-preview
      - gemini-3-flash-preview
      - gemini-2.5-pro
      - gemini-2.5-flash
      - gemini-2.5-flash-image
      # Gemini (google/ prefix)
      - google/gemini-3.1-pro
      - google/gemini-3.1-flash-lite
      - google/gemini-3-pro
      - google/gemini-3-pro-mcpmark
      - google/gemini-3-flash
      - google/gemini-2.5-pro
      - google/gemini-2.5-flash
      # DeepSeek
      - deepseek-v3.2
      - deepseek-v3.2-exp
      - deepseek-r1-0528
      - deepseek-ocr
      - deepseek/deepseek-v3.2
      - deepseek/deepseek-v3.2-exp
      - deepseek/deepseek-v3.2-exp-thinking
      - deepseek/deepseek-r1
      - deepseek/deepseek-r1-0528
      # Grok (xAI)
      - grok-code-fast-1
      - grok-4-1-fast-reasoning
      - grok-4-1-fast-non-reasoning
      - grok-4.20-beta-0309-reasoning
      - grok-4.20-beta-0309-non-reasoning
      - x-ai/grok-4.1-fast
      - x-ai/grok-code-fast-1
      # Kimi / Moonshot
      - Kimi-K2.6
      - kimi-k2.5-thinking
      - kimi-k2.5
      # MiniMax
      - MiniMax-M2.7
      - minimax-m2.5
      - minimax-m2.1
      - minimax/minimax-m2.7
      - minimax/minimax-m2.5
      - minimax/minimax-m2.1
      # GLM (Zhipu)
      - glm-5.1
      - glm-5
      - glm-5-turbo
      # Qwen (Alibaba)
      - qwen3.6-plus
      - qwen3.5-plus
      - qwen3.5-397b-a17b
      # MiMo (Xiaomi)
      - mimo-v2-pro
      - mimo-v2-omni
      - mimo-v2-flash
      - xiaomi/mimo-v2-flash

Tip: The list above covers the majority of models Aiberm currently provides, which is quite extensive. We recommend keeping only the models you actually use and removing the rest.

Field Reference

Field	Required	Description
`base_url`	Yes	Aiberm’s OpenAI-compatible endpoint. Set to `https://aiberm.com/v1`.
`api_key`	Yes	Your Aiberm API key, available from the console.
`type`	Yes	Protocol type. Set to `openai` — Aiberm conforms to the OpenAI Chat Completions specification.
`default_model`	Yes	The model used when no explicit model is specified.
`models`	Recommended	The list of models displayed in the `/model` picker. Hermes only shows entries present in this list (plus `default_model`). If omitted, the picker displays a single button.

The top-level model: section designates the active provider and default model. If you were previously using another provider, set provider: to aiberm and set default: to any model listed in the models: block.

Usage

After updating the configuration, restart Hermes (CLI: exit and re-run hermes; gateway: hermes gateway restart).

In the terminal (CLI):

/model

Hermes opens an interactive model picker. Select Aiberm, then choose the desired model. You may also switch directly:

/model claude-opus-4-7
/model gpt-5.4 --global

Adding --global persists the change to config.yaml; omitting it applies the change only to the current session.

In Telegram, Discord, Slack, or WhatsApp:

Send /model to your bot. It returns an inline keyboard listing every provider for which credentials are configured. Select Aiberm to view the paginated model list (8 per page, with Prev / Next navigation), then tap a model to switch.

Telegram /model picker showing Aiberm's paginated model list

Viewing the Complete Model Catalog

The models: list above is a curated subset. To view every model currently served by Aiberm, query the API directly:

curl -H "Authorization: Bearer sk-your-aiberm-api-key" \
     https://aiberm.com/v1/models | jq -r '.data[].id'

Add any model IDs you want to use to your models: block and restart Hermes. They will then appear in the /model picker.

Using Environment Variables (Optional)

If you prefer not to store the API key in config.yaml, you can read it from an environment variable. Set:

export AIBERM_API_KEY=sk-your-aiberm-api-key

Then reference it in config.yaml via key_env:

providers:
  aiberm:
    base_url: https://aiberm.com/v1
    key_env: AIBERM_API_KEY
    type: openai
    default_model: claude-sonnet-4-6

Troubleshooting

`/model` only shows a single button for Aiberm

The providers.aiberm block is missing the models: list. The Hermes picker only paginates when more than 8 models are configured. Add the curated list shown above and restart Hermes.

401 Unauthorized

Verify the API key at the Aiberm console.
Confirm the key is placed under providers.aiberm.api_key, not at the top level of the configuration.

Model Not Found

Aiberm’s model catalog evolves over time; a model you had listed may have been renamed or deprecated. Query /v1/models again (see above) and update your models: list accordingly.

How to verify the configuration is loaded

hermes doctor

This command prints a diagnostic report that includes the currently active provider and model.