Inference Providers documentation
Hermes Agent
Get Started
Guides
Your First API CallBuilding Your First AI AppStructured Outputs with LLMsFunction CallingResponses API (beta)How to use OpenAI gpt-ossBuild an Image EditorAutomating Code Review with GitHub ActionsAgentic Coding Environments with OpenEnvEvaluating Models with Inspect
Integrations
OverviewAdd Your IntegrationClaude CodeHermes AgentNeMo Data DesignerMacWhisperOpenCodePiVision AgentsVS Code with GitHub Copilot
Inference Tasks
Providers
CerebrasCohereDeepInfraFal AIFeatherless AIFireworksGroqHyperbolicHF InferenceNovitaNscaleOVHcloud AI EndpointsPublic AIReplicateSambaNovaScalewayTogetherWaveSpeedAIZ.ai
Hub APIRegister as an Inference ProviderHermes Agent
Hermes Agent is an open-source AI agent CLI by Nous Research for coding, research, and development tasks in the terminal.
Overview
Hermes Agent natively supports Hugging Face Inference Providers, giving you access to 100s of open models from 17+ providers through a single interface.
Prerequisites
- Hermes Agent installed (installation guide)
- A Hugging Face account with API token (needs “Make calls to Inference Providers” permission)
Configuration
Add your token to ~/.hermes/.env:
HF_TOKEN=hf_...Then select Hugging Face as your provider via hermes model, or pass it directly:
hermes chat --provider hf
For full configuration options including routing suffixes and permanent config, see the Hermes Agent HF configuration guide.