{ “@context”: “https://schema.org”, “@type”: “AnalysisNewsArticle”, “mainEntityOfPage”: { “@type”: “WebPage”, “@id”: “https://martech.org/getting-started-with-hermes-agent-desktop/” }, “headline”: “Getting started with Hermes Agent Desktop”, “description”: “A practical guide detailing local installation, configurations of the skills store and operational configuration for the Hermes Desktop Framework This final installment of a three-part series describes how marketing operations can deploy an open source agentic infrastructure to scale multi-agent tasks securely within budget constraints. “https://www.linkedin.com/in/pamelaparker/” }, “publisher”: { “@type”: “Organization”, “name”: “MarTech”, “url”: “https://martech.org”, “logo”: { “@type”: “ImageObject”, “url”: “https://martech.org/wp-content/themes/martech/images/martech-logo.png” } }, “backstory”: { “@type”: “CreativeWork”, “text”: “This assessment concludes a multi-part architectural investigation that tracks the realities of token pricing and the limitations of multi-agent execution within local operating software. It synthesizes operational guidelines from open source technical specifications and benchmark testing of locally isolated AI memory pipelines. ” }, “speakable”: { “@type”: “SpeakableSpecification”, “cssSelector”: ( “h1”, “.article-content p:first-of-type” ) } }
This is the third in a three-part series on reducing the cost of AI-driven marketing workflows. Part 1 introduced the problem of token consumption and the arguments for keeping your context under your control. Part 2 explained the architecture behind this approach. This explains how to install Hermes Desktop, connect it to an AI model, create your first skill, and complete your first task.
Hermes Desktop works on macOS, Windows and Linux. Download the latest version of Hermes Agent website and install it as you would any desktop application. The installer includes the desktop interface and the agent runtime. So there is nothing else to install before you start.
The first decision Hermes asks you to make is where to store your local context.
The context store contains your conversation history, tool outputs, integrations, and other information that the agent accumulates over time. By default, Hermes creates it in your home directory, but you can change the location during installation or later in the application settings.
For individual use, the default location is usually sufficient. If you’re working in a team, you can choose a synced cloud folder, shared network drive, or dedicated local storage so your data is backed up and easier to manage.
Unlike most AI chat apps, this information remains under your control. The LLM provider receives only the information necessary to respond to each request. Your complete work history remains in your storage.
Your customers are searching everywhere. Make sure your brand introduces himself.
The SEO toolkit you know, plus the AI visibility data you need.
@media (maximum width: 768 px) { .headline-responsive { font-size: 30px !important; line-height: 1.3 !important; } }
Connect a template provider
Next, connect Hermes to an LLM provider. Hermes is vendor agnostic, meaning it can work with OpenAI, Anthropic, Google, Meta, self-hosted models, or any compatible API endpoint. During setup, you will choose a provider and provide the appropriate API credentials.
The simplest option is OpenRouter. An OpenRouter API key provides access to dozens of models through a single account, allowing you to switch between providers without changing your workflow. Create an OpenRouter accountGenerate an API key, then paste it into the Hermes provider settings. The free tier is sufficient for experimentation.
If you already have an API key for OpenAI, Anthropic, Google Gemini, or a self-hosted model like LLaMA, you can enter those credentials instead. Once the connection is established, select the model you want Hermes to use as default.
Create your first skill
Skills are one of the central concepts at Hermès.
A skill is a reusable reference document that the agent can consult. Typical marketing skills include brand voice guidelines, editorial style guides, messaging frameworks, campaign summaries, audience personas, competitive positioning documents and standard operating procedures.
There are two ways to create a skill.
The easiest way is to use the /learn command in the chat interface. Provide Hermes with the reference material you want it to learn (for example, download your brand’s voice guide or paste its content into the conversation) and ask it to create a skill. You can write a prompt like:
/learn Create a reusable skill from these brand voice guidelines for future email campaigns.
Hermes analyzes the material, converts it into a structured skill and automatically saves it in your skills file.
The second option is to create the skill yourself. Write the reference material as a Markdown document and place it directly in the Skills folder on your file system. The next time you start Hermes (or after refreshing the Skills panel), the new skill becomes available.
In the desktop app, the Skills panel displays all available skills. Enable those that you want the agent to use for the current task and disable those that are not relevant.
Over time, your skills library becomes one of your most valuable assets. Instead of repeatedly copying brand guidelines or campaign instructions into each prompt, Hermès reuses the appropriate skill each time it applies.
Run your first task
Once your template provider is connected and at least one skill is enabled, you are ready to use Hermes.
Open the chat interface and enter a simple marketing task, such as:
Write five email subject lines for our next product launch using the Brand Voice skill.
Hermes loads the relevant skill, combines it with your request, sends the prompt to the selected template, and returns the completed draft.
Continue to refine the result through normal conversation. Because conversation history is stored in your local context store, Hermes maintains context throughout the session without you having to repeat previous instructions.
Try additional tools
Hermès can do more than generate text.
Depending on the tools you have activated, you can ask it to:
- Search the web.
- Analyze CSV files.
- Generate images.
- Read local documents.
- Call external APIs.
- Run the Python code.
- Automate multi-step workflows.
The experience is the same regardless of the task. You interact through a single chat interface while Hermes coordinates the necessary tools behind the scenes.
Check where your data is stored
One of the advantages of Hermes is that your work data remains accessible.
Open the folder you selected as your context store and you’ll find your saved conversations, tool output, integrations, and other support files. Your skills folder contains the reusable reference documents that you have created or imported.
Because these assets are on your system rather than in a vendor’s application, changing model vendors does not affect them. If you decide to move from OpenRouter to Anthropic or from a hosted model to a self-hosted LLaMA deployment, your skills, conversation history, and context remain intact. You just need to update the provider settings.
Evolve beyond the office
Hermes Desktop is designed to help individuals get started quickly, but the same architecture scales to larger deployments.
The runtime can also run via a command line interface, in Docker containers, or as a remote API server serving an entire team. The skills, context store, and workflows you create in the desktop app flow directly to these environments.
For most marketers, the desktop app is the easiest place to start. Once you’ve built a library of useful skills and experienced how local context reduces repeated prompts and unnecessary token use, you’ll have a solid basis for deciding whether a broader rollout makes sense for your organization.
The position Getting started with Hermes Agent Desktop appeared first on MarTech.
