Hermes Agent logo
AI agents

Use TokenRex with Hermes Agent

Connect Nous Research's Hermes Agent to TokenRex through a custom OpenAI-compatible endpoint.

Setup checked against the linked documentation. Screenshots are reference examples from the tool's publisher, not proof of a TokenRex connection. Live execution inside this third-party app has not been tested; verify a short request before running larger tasks.

Before you start

  • Hermes Agent installed on Linux, macOS or Windows with WSL2
  • A TokenRex API key
  • An enabled chat model with tool calling and enough context for agent tasks

Setup methods

1

Interactive model picker

  1. 1.

    Install Hermes using its official instructions; review any installer before running it.

  2. 2.

    Outside an active chat, run hermes model and choose Custom endpoint.

  3. 3.

    Enter https://tokenrex.ai/api/public/v1, your private TokenRex key and an exact enabled model ID. Choose the Chat Completions API mode.

  4. 4.

    Set context and output limits only from the selected model's verified specifications. Start hermes and test a short message.

Hermes dashboard model picker
Official Hermes model picker. Custom endpoint fields are documented separately. Official source
  1. 1Select the configured model for the main agent.
  2. 2Check context and capabilities against the model's actual specifications.
Setup reference
2

Configuration file

  1. 1.

    Save TOKENREX_API_KEY in ~/.hermes/.env or the private environment used by Hermes.

  2. 2.

    Merge the model block into ~/.hermes/config.yaml and restart Hermes.

  3. 3.

    Use api_mode: chat_completions. Change protocols only when the endpoint and selected model support them.

Configuration
yaml
model:
  provider: custom
  default: openai/gpt-6-astra
  base_url: https://tokenrex.ai/api/public/v1
  api_mode: chat_completions
  key_env: TOKENREX_API_KEY
Setup reference
3

Named provider and in-chat switching

  1. 1.

    Add the named provider block below to config.yaml and keep the key in TOKENREX_API_KEY.

  2. 2.

    Select /model custom:tokenrex:openai/gpt-6-astra in chat.

  3. 3.

    The dashboard model picker is another supported interface; choose the same endpoint and compatible transport there.

Configuration
yaml
providers:
  tokenrex:
    api: https://tokenrex.ai/api/public/v1
    key_env: TOKENREX_API_KEY
    transport: chat_completions
Setup reference

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.