Terminal AI coding assistant by Nous Research
Hermes Agent is a terminal AI coding tool that connects to Qwen Cloud through pay-as-you-go, Coding Plan, or Token Plan (Team Edition).
Run
Replace
Replace
Replace
Send a test message to verify your configuration:
A successful response confirms the configuration works. To switch models, use the
For configuration errors, check the FAQ for your billing plan:
Hermes Agent defaults to OpenRouter. To use Qwen Cloud, set
Install Hermes Agent
- Run this command to install Hermes Agent. The script automatically installs dependencies like Python and Git.
Windows does not support native installation. Install WSL2 first, then run the above command in WSL2.
- After installation, reload the terminal environment.
- Verify the installation. A version number confirms success.
Configure access credentials
Run hermes config set to configure the Base URL and API Key for your chosen plan:
- Token Plan (Team Edition): Seat-based subscription; token consumption deducts Credits.
- Coding Plan: Fixed monthly subscription, metered by model invocation count.
- Pay-as-you-go: Post-paid based on actual usage.
Token Plan (Team Edition)
Replace YOUR_API_KEY with your Token Plan (Team Edition) API Key. Available models are listed in supported models.
Coding Plan
Replace YOUR_API_KEY with your Coding Plan API Key. Available models are listed in supported models.
Pay-as-you-go
Replace YOUR_API_KEY with your Qwen Cloud API Key. Available models are listed in Anthropic compatible API.
Set base_url for your region. The API Key must match the selected region:
- Singapore:
https://dashscope-intl.aliyuncs.com/apps/anthropic
Verify configuration
Send a test message to verify your configuration:
-m parameter:
FAQ
Error codes
For configuration errors, check the FAQ for your billing plan:
- Pay-as-you-go: Error codes and troubleshooting
- Coding Plan: Coding Plan FAQ
- Token Plan (Team Edition): Token Plan (Team Edition) FAQ
Still connecting to OpenRouter after configuration
Hermes Agent defaults to OpenRouter. To use Qwen Cloud, set model.provider to custom: