Skip to main content
Connect OverControl to Hermes Agent and use Lume models directly inside your coding workflow. Hermes Agent supports a custom OpenAI-compatible endpoint, so you can connect it to OverControl using your API key, the OverControl Base URL, and a Lume model ID.
This guide covers Hermes Agent in the terminal.

​
Before you start

You need:

Open the API dashboard

Create and manage the API key you will use with Hermes Agent.

​
1. Install Hermes Agent

On macOS or Linux:
On Windows, open PowerShell and run:
When the installer finishes, open a new terminal.

​
2. Choose a custom endpoint

Run:
Choose Custom endpoint.

​
3. Configure OverControl

Enter the following values: For most coding workflows, start with Lume 3.5. Lume 3.5 has a 400,000-token context window, so enter 400000 when Hermes asks for the context length.
Keep your API key private. Never expose it in screenshots, logs, public configuration files, or source-control repositories.
Hermes saves the endpoint on your machine.

​
4. Verify the connection

Start Hermes:
Send a simple task:
If Hermes returns a response using the selected Lume model, the integration is ready.

​
Working with Hermes Agent

Once connected, Hermes Agent can use OverControl while helping you:
  • understand unfamiliar code;
  • explain files and functions;
  • plan implementations;
  • debug issues;
  • review or refactor code;
  • write tests;
  • draft technical documentation;
  • reason about architecture.
Hermes Agent can also inspect files, propose edits, and run commands as part of a task.
Review file changes and terminal commands before approving them, especially when working with sensitive projects or production systems.

​
Choose a model

For most coding workflows, start with Lume 3.5. Use Lume 3.5 Max when the task needs more reasoning, for debugging, architecture, or a longer chain of steps.
Run hermes model again, choose Custom endpoint, and enter that model name. Keep the same base URL, API key, display name OverControl, and context length of 400000. Compare Lume models

​
Troubleshooting

Open a new terminal and run the command again. On bash, reload the shell with source ~/.bashrc. On zsh, reload it with source ~/.zshrc.
Check that your OverControl API key was copied correctly and has not been revoked.You can create or manage keys from the API dashboard.
Confirm that Custom endpoint is selected and that the base URL is:
Also check your network connection and API key.
Make sure the model ID is entered exactly as documented.
View available models
Run hermes model, choose Custom endpoint, and set the context length to:
Lume 3.5 and Lume 3.5 Max both use a 400,000-token window.
Check your selected model, API key, available quota or balance, and API usage in the OverControl dashboard.

​
Next steps

AI coding tools

Return to the AI coding tools overview.

Models

Choose the Lume model for your coding workflow.

Integrations

Explore all supported integrations.