---
title: "Hermes Agent setup"
description: "Configure Hermes Agent for Infistar and check the address, key and model."
lastUpdated: 2026-10-22
---

Install Hermes using the [official quickstart](https://hermes-agent.nousresearch.com/docs/getting-started/quickstart). Run `hermes model` and choose the custom endpoint option.

Set the base URL to `https://infistar.ai/v1`, enter your Infistar key, and choose the exact model ID. Save the configuration, then start Hermes using the command supported by your installed version.

Hermes can use files, terminal tools, skills and memory. Test a simple reply first, then enable the actions you need. Choose a model with enough context and tool support for your workload.


## Check the connection

Use an exact model ID available to your key, and begin with a short text request. For coding agents, first ask for a reply without reading or changing files or running commands. A successful text reply does not verify every tool or multimodal feature.

For 401, check the key and its status. For 404, check the address and protocol. For model errors, recheck the model ID and selected group. See [HTTP troubleshooting](/en/troubleshooting/http-status-troubleshooting).

[Upstream documentation](https://hermes-agent.nousresearch.com/docs/user-guide/configuration/).