Hermes Agent Integration

Hermes Agent supports custom OpenAI-compatible endpoints, so it can use Claude and GPT models through Halfbill.

Install

Follow the installation instructions, then open a new terminal and check:

hermes --version

Configure the connection

Run hermes setup and choose Custom OpenAI-compatible endpoint. Enter:

You can also configure the files directly. Merge the following into ~/.hermes/config.yaml:

model:
  provider: custom
  default: claude-sonnet-5
  base_url: https://api.halfbill.uk/v1
terminal:
  backend: local

Store the credentials in ~/.hermes/.env:

OPENAI_API_KEY=your_api_key
OPENAI_BASE_URL=https://api.halfbill.uk/v1

Keep the credentials file private. HERMES_HOME can point Hermes at a separate configuration directory.

Start coding

cd your-project
hermes chat

For a single task that exits when finished:

hermes chat --oneshot -q "Fix the failing test and run it again"

Use --toolsets terminal,file to limit a session to shell and file tools. You can change the model for a session with --model.

Verify the connection

Open a small project and ask the agent to read a file, make a change, and run its tests. Review the diff and test output, then check the request in your Halfbill dashboard. Choose other models from the catalogue.

Troubleshooting

Run hermes doctor to inspect the configuration. Missing credentials for optional providers do not prevent your configured custom endpoint from working.

If requests use another provider, check both model.provider: custom and model.base_url. If TypeScript tests fail before running, check the Node.js version inside Hermes's terminal tool; it can differ from the version in your outer shell.