What is Hermes Agent?

Hermes Agent is an open-source AI agent developed by Nous Research, designed to execute tasks, retain knowledge gained, and evolve over time. By leveraging tools such as the terminal, browser, file system, web search, and code execution, it performs actual work rather than simply generating text responses.

What is an AI agent?

Unlike standard text-generation models, an AI agent can pursue goals autonomously. It determines necessary actions, utilizes available tools, observes outcomes, and continues iterating until the objective is met.

While many AI agents already possess the capability to use tools and handle multi-step tasks, the critical distinction lies in their behavior after a task is completed. Some agents approach every new task as a fresh problem, whereas Hermes is engineered to retain valuable knowledge and procedures, thereby increasing its utility over time. For insights into how this applies to running agents on DaDesktop, refer to Agentic AI.

What sets Hermes apart?

Hermes features an integrated learning loop. It is capable of generating skills from practical experience, refining those skills during execution, storing pertinent information, and retrieving data from previous sessions when necessary.

Why use Hermes Agent?

Hermes is particularly valuable for tasks involving multiple steps, tools, or applications. Instead of manually switching between an AI chat interface, terminal, browser, and file explorer, you can assign the overall objective to Hermes and allow it to coordinate the execution.

• Handle complete tasks: Provide Hermes with a high-level objective rather than step-by-step instructions.
• Maintain long-term context: Preserve relevant information across separate sessions.
• Create reusable workflows: Store successful strategies as skills to avoid re-solving identical problems.
• Automate routine work: Schedule tasks to execute automatically in the background.
• Delegate responsibilities: Utilize separate sub-agents for different components of a complex task.
• Select your model: Connect Hermes to local models or supported cloud-based model providers.

Capabilities of Hermes

• Software development: Analyze code, debug issues, implement changes, execute tests, and manage repositories.
• Research: Search the web, review sources, aggregate data, and structure findings.
• Automation: Execute scripts and schedule recurring tasks such as reporting, monitoring, and other routine operations.
• System administration: Utilize the terminal, install software, configure systems, and resolve technical issues.
• Browser automation: Navigate websites, interact with web elements, and gather information.
• File management: Read, create, edit, search, and organize files.
• Tool integrations: Connect additional services and tools via MCP.

How Hermes evolves through use

Consider assigning Hermes a complex task requiring multiple steps. During the resolution process, Hermes may identify an effective workflow. Rather than losing this insight upon task completion, it can save the workflow as a skill.

When a similar task arises, Hermes can leverage this saved skill as a foundation. If the workflow requires optimization, the skill can be updated accordingly. Its memory also captures useful facts and lessons learned from prior work.

Memory and skills serve distinct functions: memory stores contextual information, while skills store procedural methods. Together, they enable Hermes to accumulate comprehensive knowledge about both what it knows and how to perform recurring tasks.

Automate background work

Hermes includes a built-in scheduler for recurring tasks. You can define schedules using natural language, allowing Hermes to perform work independently without requiring an active session start.

This functionality is ideal for generating reports, monitoring systems, performing backups, conducting research, and handling other routines. Scheduled tasks can maintain continuity between executions, enabling them to build upon previous results.

Run local or cloud models

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

Utilizing a local model provides greater control over the model, hardware, and data processing location. It also allows Hermes to interact with your files and local resources without transmitting them to external model providers.

Installing Hermes

Hermes is compatible with Linux, macOS, Windows, and WSL2. You may choose to install the desktop application or utilize the command-line version without the GUI.

To install on Linux, macOS, or WSL2, open a terminal and execute the following command:

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

On Windows, run the installer via PowerShell using:

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

Once installed, launch the setup wizard to configure your model provider and other settings:

hermes setup

For detailed installation options and configuration guides, consult the Hermes documentation.

Running Hermes on DaDesktop

Hermes requires an environment capable of running its tools and storing data. DaDesktop offers a cloud desktop equipped with the necessary CPU, RAM, storage, and GPU resources to run Hermes alongside a local LLM.

This setup is beneficial when the selected model requires more VRAM than your local hardware can provide. You can select a GPU with sufficient VRAM, launch a DaDesktop environment, install Hermes, and run the model locally in tandem with the agent.

Additionally, you can keep the desktop active for scheduled tasks and long-running workflows, eliminating the need to keep your personal computer powered on.

Learn more about running local LLMs on DaDesktop.