What is Hermes Agent?

Developed by Nous Research, Hermes Agent is an open-source AI agent designed to execute complex tasks, retain knowledge, and evolve its capabilities over time. Rather than limiting itself to generating text responses, it leverages a diverse toolkit—including terminals, browsers, file systems, web search, and code execution—to accomplish real-world work.

What is an AI agent?

An AI agent goes beyond simple text generation. When provided with a specific objective, it can independently determine the necessary actions, utilize available tools, observe outcomes, and persistently work toward achieving the goal.

While many AI agents are capable of using tools and completing multi-step tasks, the distinction lies in what happens once the task is complete. Some agents treat every assignment as a fresh, isolated problem. In contrast, Hermes is engineered to retain valuable knowledge and procedures, making it progressively more effective. For insights into how this applies to running agents on DaDesktop, see Agentic AI.

What sets Hermes apart?

Hermes features an integrated learning loop. It can generate skills from practical experience, refine these skills during operation, memorize pertinent information, and query previous sessions when it requires data from earlier interactions.

Why choose Hermes Agent?

Hermes is particularly valuable when a task involves multiple steps, tools, or applications. Rather than constantly switching between an AI chat, terminal, browser, and file system, you can delegate the overall objective to Hermes and allow it to coordinate the necessary actions.

• Work on complete tasks: Assign Hermes a broader objective rather than requesting individual instructions.
• Keep context over time: Retain useful information across separate sessions.
• Build reusable workflows: Save successful approaches as skills to avoid solving the same problem from scratch repeatedly.
• Automate recurring work: Schedule tasks to execute automatically in the background.
• Delegate work: Utilize separate subagents to handle different components of a larger project.
• Choose your model: Connect Hermes to local models or supported cloud model providers.

What Hermes can do

• Software development: Inspect code, debug issues, implement changes, run tests, and manage repositories.
• Research: Search the web, analyse sources, gather information, and organise findings.
• Automation: Execute scripts and schedule recurring tasks such as reports, monitoring, and other routines.
• System administration: Use the terminal, install software, configure systems, and troubleshoot issues.
• Browser tasks: Navigate websites, interact with web pages, and collect information.
• File work: Read, create, edit, search, and organise files.
• Tool integrations: Connect additional services and tools through MCP.

How Hermes improves with use

Consider a scenario where you assign Hermes a complex task requiring several steps. During the process, Hermes may identify an effective workflow. It can preserve this workflow as a skill, ensuring the knowledge is not lost once the task is completed.

When a similar task arises in the future, Hermes can leverage that saved skill as a starting point. If the workflow requires refinement, the skill can be updated. Additionally, its memory can retain useful facts and lessons learned from previous work.

Memory and skills serve distinct purposes. Memory holds useful information and context, whereas skills store procedures for performing tasks. Together, they enable Hermes to build comprehensive knowledge about both what it knows and how to execute recurring work.

Automate work in the background

Hermes includes a built-in scheduler for recurring tasks. You can describe a schedule in natural language, and Hermes will perform the work without waiting for you to initiate a session.

This feature is ideal for reports, monitoring, backups, research tasks, and other routines. Scheduled tasks can also maintain continuity between runs, allowing them to build upon previous work.

Run local or cloud models

Hermes is not restricted to a single LLM. You can connect it to local models or supported cloud providers and switch models without altering the agent's tools, memory, or workflows.

Running a local model provides greater control over the model, hardware, and data processing location. It also allows Hermes to work with your files and other local resources without transmitting them to an external model provider.

How to install Hermes

Hermes is compatible with Linux, macOS, Windows, and WSL2. You can install the desktop application or utilize the command-line version without the desktop interface.

On Linux, macOS, or WSL2, open a terminal and run:

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

On Windows, run the installer from PowerShell:

irm https://hermes-agent.nousresearch.com/install.ps1 | iex

After installation, run the setup wizard to configure your model provider and other options:

hermes setup

Refer to the Hermes documentation for detailed installation options and configuration instructions.

Run Hermes on DaDesktop

Hermes requires an environment where it can execute its tools and maintain its data. DaDesktop provides a cloud desktop equipped with the CPU, RAM, storage, and GPU resources necessary to run Hermes alongside a local LLM.

This is particularly useful when the model you wish to run requires more VRAM than your local machine offers. Select a GPU with sufficient VRAM, launch a DaDesktop desktop, install Hermes, and run the model locally alongside the agent.

You can also keep the desktop active for scheduled tasks and long-running workflows without needing to leave your personal computer powered on.

Learn more about running local LLMs on DaDesktop.