What is Hermes Agent?

Hermes Agent is an open-source AI agent developed by Nous Research, designed to execute complex tasks, retain learned knowledge, and evolve over time. Rather than simply generating responses, it leverages tools such as terminals, browsers, file systems, web search, and code execution to actively carry out work.

What is an AI agent?

An AI agent goes beyond basic text generation. When provided with a specific goal, it autonomously determines the necessary actions, utilises available tools, observes outcomes, and continues its workflow until the objective is achieved.

While many AI agents are already capable of using tools to complete multi-step tasks, the critical distinction lies in what happens afterwards. Some agents approach each task as an isolated problem. In contrast, Hermes is engineered to retain useful knowledge and procedures, becoming increasingly valuable over time. For more insights on this concept in the context of running agents on DaDesktop, refer to Agentic AI.

What distinguishes Hermes?

Hermes features an integrated learning loop. It generates skills from experience, refines them during application, stores pertinent information, and retrieves details from prior sessions when necessary.

Why choose Hermes Agent?

Hermes is particularly effective for tasks involving multiple steps, tools, or applications. Instead of manually switching between AI chats, terminals, browsers, and files, you can assign the overarching task to Hermes and allow it to coordinate the process.

• Handle complete tasks: Assign Hermes a high-level objective rather than requesting individual step-by-step instructions.
• Maintain long-term context: Preserve useful information across separate sessions.
• Create reusable workflows: Store successful strategies as skills to avoid re-solving identical problems from scratch.
• Automate recurring duties: Schedule tasks to execute automatically in the background.
• Delegate components: Utilise separate subagents for different parts of a larger project.
• Select your model: Integrate Hermes with local models or supported cloud-based model providers.

Hermes capabilities

• Software development: Analyse code, debug issues, implement changes, execute tests, and manage repositories.
• Research: Perform web searches, review sources, gather data, and organise findings.
• Automation: Execute scripts and schedule recurring activities such as reporting, monitoring, and other routine operations.
• System administration: Operate terminals, install software, configure systems, and troubleshoot issues.
• Browser interactions: Navigate websites, interact with web pages, and extract information.
• File management: Read, create, edit, search for, and organise files.
• Tool integrations: Connect additional services and tools via MCP.

How Hermes evolves through use

Imagine assigning Hermes a complex, multi-step task. During execution, it may identify an efficient workflow. Rather than losing this insight when the task concludes, Hermes can save it as a skill.

When a similar task arises, Hermes can leverage this stored skill as a foundation. Should the workflow require refinement, the skill can be updated. Additionally, its memory preserves key facts and lessons learned from previous work.

Memory and skills serve distinct functions. Memory holds contextual information, while skills store procedural steps. Together, they enable Hermes to accumulate knowledge about both its understanding and how to perform recurring tasks efficiently.

Background task automation

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

This feature is suitable for reports, monitoring, backups, research, and other routines. Scheduled tasks can maintain continuity between runs, building upon previous work.

Local or cloud model support

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.

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

Installing Hermes

Hermes is compatible with Linux, macOS, Windows, and WSL2. You may install the desktop application or utilise the command-line version independently.

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

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

Post-installation, run the setup wizard to configure your model provider and other preferences:

hermes setup

Consult the Hermes documentation for detailed installation options and configuration settings.

Running Hermes on DaDesktop

Hermes requires an environment capable of executing 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 is particularly useful if the model you wish to run requires more VRAM than your local machine provides. Select a GPU with sufficient VRAM, launch a DaDesktop instance, install Hermes, and run the model locally alongside the agent.

You can also keep the desktop active for scheduled tasks and long-running workflows, eliminating the need to keep your personal computer running.

Discover more about running local LLMs on DaDesktop.