Skip to main content

Hermes Agent

Connect Hermes Agent to Divyam for reading files, editing code and running project commands.

Before you start

You need a Divyam account and an API key. If you don't have them yet, follow Getting Started first.

Replace the shortened divyam-sw-v1-... shown in examples with your complete API key.

The examples use divyam-as/gpt-6-sol. For another model, select its current ID in your harness or copy it from Models and pricing, and check its context limit and supported features.

1. Install Hermes Agent​

Follow the official installation instructions.

Set your key in the shell you will use to start the app:

export DIVYAM_API_KEY="divyam-sw-v1-..."

2. Configure Divyam​

divyam-as/

Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing

Merge these settings into ~/.hermes/config.yaml, updating existing sections rather than duplicating them. On native Windows, the current installer uses %LOCALAPPDATA%\hermes\config.yaml:

providers:
  divyam:
    api: https://api.preview.divyam.ai/v1
    key_env: DIVYAM_API_KEY
    transport: chat_completions
model:
  default: divyam-as/gpt-6-sol
  provider: custom:divyam
  context_length: 1048576
agent:
  reasoning_effort: none
auxiliary:
  title_generation:
    extra_body:
      temperature: 1
  compression:
    extra_body:
      temperature: 1

Keep both auxiliary temperature values at 1 for this model. Hermes uses the main provider and model for auxiliary tasks by default. The native hermes model wizard can save a custom endpoint, key and model. Save the compatibility overrides above in config.yaml.

3. Send your first prompt​

Start Hermes from the shell where you exported the key:

hermes chat
In Hermes Agent's composer
Hello, what are your capabilities?
Paste this message, then send it.

For image questions, attach an image in Hermes and ask about its contents.

Check your requests​

Open the Divyam console and select Logs. Your requests appear there within a few seconds, newest first, with their status, token counts and latency. Usage and Credits & Billing catch up within a few minutes.

Local cost estimates

Some clients display zero when model prices are missing. Check Credits & Billing for Divyam charges. Local dollar limits depend on the client's price and usage data.

For filters, cached-token counts and the requested-versus-routed view, see Logs and usage.