Skip to main content
Use AIsa in Hermes Agent with one model endpoint and one API key. AIsa endpoint:

Prerequisites

Before you start, make sure you have:
  • An AIsa API key
  • A terminal on macOS, Linux, or Windows WSL2

1. Install Hermes Agent

Run the official installer:
Reload your shell:
Verify the installation:

2. Add AIsa as the model provider

Run:
Hermes will ask you to choose a model provider. Select:
Select Custom Model / OpenAI-compatible endpoint This lets Hermes connect to AIsa through AIsa’s OpenAI-compatible API.

2.1 Configure AIsa endpoint

When Hermes asks for the API endpoint and API key, enter:
If the endpoint is valid, Hermes will show that it can access the model list from AIsa:

2.2 Choose API mode

Hermes API compatibility mode prompt Pick mode 1. Auto-detect or 2. Chat Completions — both work, since the base URL ends in /v1. Mode 2 is recommended because it’s explicit and easier to debug.
If you pick mode 4, go back to step 2.1 and remove /v1 from the base URL — Anthropic clients append /v1/messages themselves.

2.3 Choose a model

Hermes will show the available model list. You can either enter the model number or type the model name directly:
Choose a text, reasoning, or coding model. Do not choose image, video, embedding, Whisper, or TTS models as the main Hermes model.

2.4 Set context length

When Hermes asks:
Press Enter to leave it blank.

3. Connect AIsa capabilities and start using

After the model provider is configured, start Hermes:
Then paste this prompt into Hermes:
Hermes will fetch AIsa’s agent-facing instructions and guide you through the remaining setup. After that, you can start using Hermes with AIsa models and capabilities. Try:

Quick reference

Troubleshooting

Use AIsa in OpenClaw

Configure another agent runtime with the OpenClaw setup path.

Authentication

API key creation, rotation, and storage best practices.

Model Catalog

Browse supported models before choosing a Hermes default.