Integration guide · Personal agent

Hermes Agent on EU-hosted open models

Run Nous Research's Hermes Agent on a custom endpoint: Frontière AI's base URL in config.yaml, EU-hosted open models behind it. ~/.hermes/config.yaml: model.provider custom with base_url, default and key_env; or hermes model → Custom endpoint.

Settings from the official documentation, checked on 12 October 2026. Not run end to end by us.

API format

OpenAI-compatible

Base URL

https://getfrontiereai.eu/api/v1

Where it goes

~/.hermes/config.yaml: model.provider custom with base_url, default and key_env; or hermes model → Custom endpoint.

Your prompts

Straight from your machine to us

Setup

# ~/.hermes/config.yaml
model:
  provider: custom
  base_url: https://getfrontiereai.eu/api/v1
  default: glm-5.2
  key_env: FRONTIERE_API_KEY
  context_length: 256000

providers:
  frontiere:
    api: https://getfrontiereai.eu/api/v1
    key_env: FRONTIERE_API_KEY
    transport: chat_completions
    default_model: glm-5.2
    models:
      glm-5.2: { context_length: 256000 }
      qwen3.6-35b: { context_length: 262144 }

# ~/.hermes/.env
# FRONTIERE_API_KEY=sk-front-...

Which model to pick

24 live models have tool calling measured by a real call through the gateway. Models labeled EU sovereign run at European providers; fast-access models are served through US-controlled infrastructure. Prices are per 100,000 tokens, margin and VAT included.

Good to know

• Hermes needs at least 64,000 tokens of context and tool calling: smaller windows are refused at startup.
• Auxiliary tasks (vision, summaries, titles, compression) use the main model by default, so they also go to Frontière AI.
• Hermes sends reasoning_effort: medium when none is set; mark models that do not reason with supports_reasoning: false.

Where your prompts go

With a custom endpoint, Hermes sends requests to the configured URL with your key. Nous Portal routing only applies if you choose the Portal as provider.

On our side, a model labeled EU sovereign runs at a European provider, and the gateway itself runs in Paris on Vercel, a US company — our privacy page says so. Billing keeps the model, the token counts and the amount, never the prompt or the reply.

Sovereignty →Privacy →

Sources

Official documentation, checked on 12 October 2026:

• Hermes Agent — Providers
• Hermes Agent — Configuration

FAQ

Other guides

• gooseDesktop and CLI agent
• OpenClawPersonal agent