Skip to main content
Hermes Agent is a self-improving terminal agent from Nous Research with a built-in MCP client. Route its model calls through the AI Gateway, then connect it to the Orq MCP server for agentic access to the workspace.

​
Prerequisites

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

​
AI Gateway

Hermes is OpenAI-compatible, so it routes through the AI Gateway by pointing at the router endpoint. Open the config with hermes config edit and set the model block to a custom provider pointed at the router, with the Orq.ai key inline: 
model:
  provider: custom
  default: "anthropic/claude-sonnet-4-6"
  base_url: "https://api.orq.ai/v3/router"
  api_key: "<your-orq-api-key>"
Set default to any provider-prefixed model from the AI Gateway catalog.
The default config already contains a model block. Edit its existing keys, the block must end up with a single provider and a single base_url.
Every model call now routes through the Orq.ai AI Gateway and appears in Traces.

​
MCP

The Orq MCP server exposes the Orq.ai platform as MCP tools. Hermes’s built-in MCP client connects to it at startup and uses those tools to manage Agents, run experiments, and query Traces from natural language.

​
Installation

Add the Orq MCP server to ~/.hermes/config.yaml under mcp_servers: 
mcp_servers:
  orq:
    url: "https://my.orq.ai/v2/mcp"
    headers:
      Authorization: "Bearer <your-orq-api-key>"
Reload MCP servers without restarting by running /reload-mcp inside Hermes, then confirm the connection: 
hermes mcp test orq

​
Available Commands

Once connected, ask Hermes to perform operations across the workspace:
  • Create an agent with custom instructions and tools
  • Get agent configuration for [agent-key]
  • Invoke agent [agent-key] with input [message]
  • Create an experiment from dataset [dataset-key]
  • Run experiment and auto-evaluate results
  • Export experiment run [run-id] as CSV
  • Create a dataset called "customer-queries"
  • Add datapoints to dataset [dataset-key]
  • List all datapoints in dataset [dataset-key]
  • List traces from the last 24 hours
  • Show me traces with errors
  • Get span details for trace [trace-id]
  • Get analytics overview for my workspace
  • Show me workspace metrics for the last 7 days

​
See Also

Orq MCP Quickstart

The full Orq MCP tool reference.

API Keys

Create and manage Orq.ai API keys.