Back to Blog
EnglishTutorial

Hermes Agent + Crazyrouter: One-Click Setup for 627+ AI Models

Connect Hermes Agent to Crazyrouter in under a minute. One script, one API key, 627+ models — Claude, GPT, Gemini, DeepSeek, Qwen and more.

C
Crazyrouter Team
May 4, 2026 / 1129 views
Share:
Hermes Agent + Crazyrouter: One-Click Setup for 627+ AI Models

What is Hermes Agent?#

Hermes Agent is an open-source AI coding assistant that runs in your terminal. Think of it as a local, privacy-friendly alternative to cloud-based coding copilots — it connects to any OpenAI-compatible API and gives you an interactive chat or autonomous coding workflow right from the command line.

The problem? You still need an inference provider. That's where Crazyrouter comes in.

PowerShell setup flow for Hermes Agent with Crazyrouter API key entry and model selection

Why Crazyrouter + Hermes?#

Instead of juggling multiple API keys and endpoints for different model providers, Crazyrouter gives you:

  • One API key for 627+ models (OpenAI, Anthropic, Google, DeepSeek, Qwen, Meta, and more)
  • One endpoint — fully OpenAI-compatible: https://ai.crazyrouter.us/v1
  • Pay-as-you-go — no subscriptions, no minimums
  • Switch models instantly — no config changes needed

Hermes Agent speaks the OpenAI protocol natively, so the integration is seamless.

Quick Start#

Linux / macOS / WSL2#

bash
curl -fsSL https://raw.githubusercontent.com/xujfcn/crazyrouter-hermes/main/setup.sh | bash

Windows (PowerShell)#

powershell
irm https://raw.githubusercontent.com/xujfcn/crazyrouter-hermes/main/setup.ps1 | iex

Windows (CMD)#

cmd
curl -o setup.bat https://raw.githubusercontent.com/xujfcn/crazyrouter-hermes/main/setup.bat
setup.bat

The script will:

  1. Check that Hermes Agent is installed
  2. Ask for your Crazyrouter API key
  3. Let you pick a default model
  4. Write the config to ~/.hermes/
  5. Optionally test the connection

That's it. The whole process takes about 30 seconds.

What the Setup Does Under the Hood#

The script writes two files in ~/.hermes/:

.env — stores your credentials:

code
OPENAI_API_KEY=sk-your-crazyrouter-key
OPENAI_BASE_URL=https://ai.crazyrouter.us/v1

config.yaml — sets the default model:

yaml
model:
  provider: "custom"
  default: "claude-opus-4-7"
  base_url: "https://ai.crazyrouter.us/v1"

Existing configs are backed up automatically (.env.bak, config.yaml.bak).

Completed PowerShell setup screen showing Hermes Agent connected to Crazyrouter

Available Models#

During setup you can choose from popular defaults:

#ModelBest For
1claude-opus-4-7Complex reasoning, coding
2gpt-5.4General tasks, fast
3claude-sonnet-4.6Balanced speed & quality
4gemini-3.1-proMultimodal, long context
5deepseek-chatBudget-friendly reasoning
6qwen-maxChinese + English
7gpt-4oMultimodal

Or enter any model name from the full catalog — all 627+ are available.

Switching Models After Setup#

Once configured, switch models anytime:

bash
hermes model             # interactive picker
hermes model list        # see all available models

Or just edit ~/.hermes/config.yaml and change the default field. No restart needed.

Prerequisites#

  • Hermes Agent installed
  • A Crazyrouter API key — get one free (includes starter credit)
  • curl (Linux/macOS) or PowerShell 5+ (Windows)

Troubleshooting#

"Hermes Agent not found" — Install Hermes first:

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

Connection test fails — Double-check your API key at crazyrouter.com/dashboard. Make sure you have credit on your account.

Want to reset? — Run the setup script again. It backs up your old config and writes fresh files.

Source Code#

The setup scripts are fully open-source (MIT):

👉 github.com/xujfcn/crazyrouter-hermes

Supports Linux, macOS, WSL2, Windows PowerShell, and Windows CMD.

Get Started#

  1. Get your API key at crazyrouter.com
  2. Run the one-liner for your platform
  3. Start coding with hermes

One key. 627+ models. Zero friction.

Implementation Guides

Related Articles

One API Key for GPT, Claude and Gemini: A Practical Setup for Central Asia DevelopersTutorial

One API Key for GPT, Claude and Gemini: A Practical Setup for Central Asia Developers

A practical tutorial for developers in Central Asia who want to call GPT, Claude and Gemini from one OpenAI-compatible API gateway.

May 22
AI API Gateway for Singapore and Malaysia Developers: One Endpoint for GPT, Claude and GeminiTutorial

AI API Gateway for Singapore and Malaysia Developers: One Endpoint for GPT, Claude and Gemini

A practical setup guide for Singapore and Malaysia developers who want one OpenAI-compatible endpoint for GPT, Claude and Gemini.

May 22
How to Get a Claude API Key in 2026: Official Setup, Alternatives, and Tested ExamplesTutorial

How to Get a Claude API Key in 2026: Official Setup, Alternatives, and Tested Examples

"Learn how to get a Claude API key in 2026 from Anthropic or through Crazyrouter. Includes official setup steps, tested API examples, common problems, and a direct-vs-gateway comparison."

Mar 15
How to Get a Claude API Key in 2026: Setup, Security, Rotation, and AlternativesTutorial

How to Get a Claude API Key in 2026: Setup, Security, Rotation, and Alternatives

A step-by-step guide to getting a Claude API key, storing it safely, rotating it in production, and using safer alternatives for team apps.

May 23
Build a World Cup Odds Movement Monitor with Claude Code and claude-fable-5Tutorial

Build a World Cup Odds Movement Monitor with Claude Code and claude-fable-5

A second Claude Code project in the World Cup analytics series: build an odds movement monitor, compute implied probability shifts, and use claude-fable-5 through Crazyrouter to generate validated JSON analysis without betting advice.

Jun 13
Suno Music API Tutorial: Generate AI Music Programmatically in 2026Tutorial

Suno Music API Tutorial: Generate AI Music Programmatically in 2026

"Learn how to use the Suno Music API to generate songs, lyrics, and instrumentals with code. Includes Python examples, pricing, and integration tips."

Feb 21