Zeltro › Hermes Agent in Zeltro: Nous Research's open agent, on your own computer

Hermes Agent in Zeltro

How Zeltro runs Nous Research's Hermes Agent: sign in with a Nous Portal or ChatGPT plan, use an API key or OpenRouter, or a free local model in Ollama or LM Studio. Set up for you.

Hermes Agent is Nous Research's open-source agent, with a full set of coding tools. It can sign in with a Nous Portal or ChatGPT plan, take a key from OpenAI, Anthropic, Google or OpenRouter, or run a model on your own computer.

Connect it with

Your planSign in with Nous Portal / ChatGPT
An API keyOpenRouter · OpenAI · any OpenAI-compatible server
A model on your computerOllama or LM Studio
Hermes Agent Nous Research hermes Zeltro installs it hermes-agent.nousresearch.com
Your project in Zeltro
  • Runtime and database ready
  • AGENTS.md to read
  • Live preview

What Zeltro does for Hermes Agent#

  1. Installs it

    Choose Hermes Agent when Zeltro first opens, or later in Settings → AI Profiles. Zeltro installs it with Nous Research's own script, which needs curl and git and runs on Linux, macOS or WSL.

  2. Connects it

    Sign in with your Nous Portal or ChatGPT plan, or pick where a key comes from: OpenRouter, OpenAI, Ollama, LM Studio or another OpenAI-compatible server.

  3. Hands it a ready project

    Every project already has its runtime, its database and a working .env, plus an AGENTS.md, which Hermes reads by itself.

  4. Runs it beside your app

    Hermes works in a real terminal next to the live preview, and you write long requests in the message box. It doesn't tell the app when a turn is done yet, so keep an eye on its terminal.

Your plan, a key, or OpenRouter#

Your plan. Choose "Sign in with my Nous Portal / ChatGPT plan" and Hermes uses the subscription you already pay for.

An API key. A prefix on the model name picks Hermes's provider: openai/, openrouter/, anthropic/ or gemini/, such as openai/gpt-5.4-mini or openrouter/qwen/qwen3-coder. In our tests Hermes worked well through OpenRouter with DeepSeek V4.1 Flash.

How do you want to connect Hermes Agent?

Sign in with my Nous Portal / ChatGPT planUses the plan you already pay for. No extra charges.
Use an API keyPay as you go: OpenRouter, OpenAI, Ollama, LM Studio.

Hermes Agent with an API key

Where the key is from

  • OpenRouter
  • OpenAI
  • Ollama
  • LM Studio
  • Another server (enter its address)

API key

The Zeltro app’s own setup screens when you choose Hermes Agent. The same choices are in Settings → AI Profiles later.

On a model on your own computer#

Choose Ollama or LM Studio in the app, or from a terminal:

ollama pull qwen3-coder:30b
zeltro ai-set --agent hermes --model qwen3-coder:30b \
  --api-base http://localhost:11434/v1 --api-key ollama

Raise Ollama's context length to at least 64k first, and use a large enough model: about 30B is roughly the floor for building an app. See cheap and local models.

From the terminal#

zeltro ai-set --agent hermes --model openai/gpt-5.4-mini --api-key sk-...
zeltro ai-set --agent hermes --model openrouter/qwen/qwen3-coder --api-key sk-or-...

Another program also calls itself hermes (Meta's JavaScript engine), so Zeltro checks that hermes --version says Hermes Agent before it runs one.

Asking before each change. By default, the AI in each project works without stopping to ask first: the Works without asking switch in the project's panel is on. Switch it off and you approve each step in Hermes's terminal. Hermes can't be told to ask for just one run, so with the switch off, its own setting decides. To change Hermes's own setting for every run, outside Zeltro too, run zeltro ai-unattended, which writes approvals.mode: off into ~/.hermes/config.yaml (turning it back on restores Hermes's smart mode).

Questions

Can Hermes Agent use my ChatGPT or Nous Portal subscription?

Yes. Choose "Sign in with my Nous Portal / ChatGPT plan" and Hermes uses the plan you already pay for. Zeltro adds nothing on top.

Which models can Hermes Agent use?

OpenAI, Anthropic, Google and OpenRouter models with a key, or a local model in Ollama or LM Studio.

Does Hermes Agent work on Windows?

Yes, inside WSL, which Zeltro sets up on Windows for you.

Build with Hermes Agent on your own computer

Install Zeltro, choose Hermes Agent, and connect your Nous Portal or ChatGPT plan, a key or a local model. Free for personal use, with no account.

Install Zeltro Why bring your own key

Rather not set it up yourself? I’ll do it for you.

Checked 2026-11-09. Other products change often — if something here is out of date, tell us and it gets fixed.