What is Hermes Agent?

Hermes Agent is an open-source AI agent from Nous Research that is built to work on tasks, remember what it learns, and improve over time. It can use tools such as a terminal, browser, file system, web search, and code execution to carry out work instead of only generating a response.

What is an AI agent?

An AI agent can do more than generate text. You give it a goal, and it can decide what actions are needed, use tools, observe the results, and continue working toward the goal.

Many AI agents can already use tools and complete multi-step tasks. The difference is what happens after the task is finished. Some agents treat each task as a new problem. Hermes is designed to retain useful knowledge and procedures so it can become more useful over time. See Agentic AI for how this applies to running agents on DaDesktop.

What makes Hermes different?

Hermes has a built-in learning loop. It can create skills from experience, improve those skills during use, remember useful information, and search previous sessions when it needs information from earlier work.

Why use Hermes Agent?

Hermes is useful when a task involves multiple steps, tools, or applications. Instead of repeatedly switching between an AI chat, terminal, browser, and files, you can give Hermes the overall task and let it coordinate the work.

• Work on complete tasks: give Hermes an objective instead of asking for individual instructions.
• Keep context over time: retain useful information across separate sessions.
• Build reusable workflows: save successful approaches as skills instead of solving the same problem from scratch.
• Automate recurring work: schedule tasks to run automatically in the background.
• Delegate work: use separate subagents for different parts of a larger task.
• Choose your model: connect Hermes to local models or supported cloud model providers.

What Hermes can do

• Software development: inspect code, debug problems, make changes, run tests, and work with repositories.
• Research: search the web, read sources, collect information, and organise findings.
• Automation: run scripts and schedule recurring tasks such as reports, monitoring, and other routines.
• System administration: use the terminal, install software, configure systems, and troubleshoot problems.
• 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

Suppose you give Hermes a difficult task that requires several steps. While solving it, Hermes may discover a workflow that works well. It can save that workflow as a skill instead of losing the knowledge when the task ends.

The next time a similar task comes up, Hermes can use that skill as a starting point. If the workflow needs improvement, the skill can be updated. Its memory can also retain useful facts and lessons from previous work.

Memory and skills serve different purposes. Memory stores useful information and context, while skills store procedures for doing things. Together, they allow Hermes to build up knowledge about both what it knows and how to perform recurring work.

Automate work in the background

Hermes has a built-in scheduler for recurring tasks. You can describe a schedule in natural language and have Hermes perform work without waiting for you to start a session.

This can be used for reports, monitoring, backups, research tasks, and other routines. Scheduled tasks can also retain continuity between runs, allowing them to build on previous work.

Run local or cloud models

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

Running a local model gives you more control over the model, hardware, and where your data is processed. It can also let Hermes work with your files and other local resources without sending them to an external model provider.

How to install Hermes

Hermes can run on Linux, macOS, Windows, and WSL2. You can install the desktop application or use the command-line version without the desktop application.

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

See the Hermes documentation for installation options and configuration details.

Run Hermes on DaDesktop

Hermes needs an environment where it can run its tools and keep its data. DaDesktop provides a cloud desktop with the CPU, RAM, storage, and GPU resources needed to run Hermes alongside a local LLM.

This is useful when the model you want to run needs more VRAM than your own machine has. Choose a GPU with enough VRAM, launch a DaDesktop desktop, install Hermes, and run the model locally alongside the agent.

You can also keep the desktop running for scheduled tasks and long-running workflows without leaving your personal computer on.

Learn more about running local LLMs on DaDesktop.