AI agents

Use TokenRex with Hermes Desktop

Use Nous Research's official desktop interface with a TokenRex custom endpoint.

Custom-provider setup is documented in the linked official sources. A live TokenRex connection from this tool has not been tested. Screenshots illustrate the publisher's interface, not a verified TokenRex session. Hermes Desktop is Nous Research's official interface to the same Hermes Agent; it shares configuration and credentials through the selected profile.

Before you start

Official Hermes Desktop for your supported operating system
A private TokenRex API key
An enabled streaming, tool-capable chat model

Setup methods

Hermes Desktop — provider settings

1
Install the official Hermes Desktop package from Nous Research for your platform. Desktop and Agent are two interfaces to the same Hermes agent.
Nous Research's official Hermes Desktop beta preview. This illustrates the Desktop interface, not custom-endpoint settings or a TokenRex connection. Official source
1. 1Install the official Desktop app for your platform.
2. 2Configure your endpoint in Settings → Providers, as described in the next steps.
2
Create a TokenRex API key and copy an exact enabled chat model ID from Models & Pricing. Replace the example ID with your selected model. Use verified context/output limits and a streaming, tool-capable model for agent tasks.
3
Open Settings → Providers → Custom Endpoints. Check Settings Applies to and select the profile you intend to configure before changing credentials.
4
Add your custom endpoint with base URL https://tokenrex.ai/api/public/v1 and your private TokenRex API key. Set API Mode to Chat Completions, not Responses API or Anthropic Messages.
5
Save the endpoint and use Test. This can make a small billable inference request; a successful model-list lookup alone does not verify chat compatibility.
6
Select the configured provider and exact model for a new Desktop conversation. Send a short message and review usage before approving actions.
7
Send a short read-only question and confirm the exact model in TokenRex usage. Test streaming and tool calls separately before allowing file, terminal or connected-account actions.

Setup reference

Reuse an existing Hermes Agent configuration

1
If Hermes Agent already works with TokenRex, keep its existing private provider configuration rather than creating a conflicting duplicate.
2
With the CLI installed, run hermes desktop to launch the official desktop interface using the existing Hermes configuration and credentials.
3
Alternatively merge the model block below into the intended profile's config.yaml, keep the key private, restart Desktop and select that profile's provider/model.

Configurationyaml

# Merge into ~/.hermes/config.yaml
model:
  provider: custom
  default: openai/gpt-6-astra
  base_url: https://tokenrex.ai/api/public/v1
  key_env: TOKENREX_API_KEY

# Set TOKENREX_API_KEY in ~/.hermes/.env (private) or the launch environment.

Setup reference

Troubleshooting

Settings saved but the chat uses another provider: Provider settings use Settings Applies to. Confirm both the settings profile and conversation profile, then select the configured model in a new conversation.
Test succeeds for discovery but chat fails: Use the explicit Chat Completions API mode and re-test the transport. Check that the endpoint serves chat/completions and the exact model is enabled.
Authentication fails: Check that the saved TokenRex key is active and belongs in the tool's API-key field, not its subscription sign-in. Remove accidental spaces, check your wallet balance, and never share the key in screenshots or exported settings.
The model is missing or the request URL returns 404: Copy an exact enabled model ID from Models & Pricing. Follow this method's URL field: some tools expect the versioned base, others the root or full completion address. Check the documented API protocol before changing the path.
Chat works but streaming or tools fail: Test a short plain-text conversation first. Confirm the selected model and installed tool version support the required protocol and capabilities. Enable agent actions only after separately checking streaming and tool calls.

Further references

Download official Hermes Desktop

Verify the connection

Send a short message with the selected model, read its response, then confirm the exact model appears in your TokenRex usage. Test streaming and tool use separately before larger agent tasks.