What is Hermes Agent?

Hermes Agent, an open-source AI agent from Nous Research, is engineered to execute tasks, retain acquired knowledge, and evolve its capabilities over time. By leveraging tools such as terminals, browsers, file systems, web search, and code execution, it moves beyond simple response generation to actively carry out work.

What is an AI agent?

AI agents possess capabilities that extend beyond text generation. When assigned a goal, an agent can autonomously determine the necessary actions, utilize available tools, observe outcomes, and persist in working toward the objective.

While many AI agents are already capable of using tools to complete multi-step tasks, the critical distinction lies in post-task behaviour. Some agents treat every engagement as an isolated problem, whereas Hermes is designed to retain valuable knowledge and procedures, thereby increasing its utility over time. See Agentic AI to understand how this applies to running agents on DaDesktop.

What makes Hermes different?

Hermes features an integrated learning loop. It generates skills based on experience, refines those skills during operation, retains useful information, and can reference previous sessions when it requires context from earlier work.

Why use Hermes Agent?

Hermes is particularly effective for tasks involving multiple steps, tools, or applications. Rather than constantly switching between AI chats, terminals, browsers, and files, you can delegate the overall objective to Hermes and allow it to coordinate the work autonomously.

• Execute complete tasks: Provide Hermes with a high-level objective rather than a series of individual instructions.
• Maintain long-term context: Retain useful information across separate sessions.
• Create reusable workflows: Save successful strategies as skills to avoid re-solving the same problem from scratch.
• Automate routine work: Schedule tasks to execute automatically in the background.
• Delegate complex work: Employ separate subagents to handle different components of a larger task.
• Select 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 data, and organise findings.
• Automation: Execute scripts and schedule recurring tasks such as reports, monitoring, and other routines.
• System administration: Utilize terminals, install software, configure systems, and troubleshoot issues.
• Browser interactions: Navigate websites, interact with web pages, and collect data.
• File management: Read, create, edit, search, and organise files.
• Tool integrations: Connect additional services and tools via MCP.

How Hermes improves with use

Consider a complex task requiring several steps. While resolving it, Hermes may identify an effective workflow. Instead of losing this knowledge when the task concludes, it can save the workflow as a skill.

When a similar task arises in the future, Hermes can utilize that skill as a baseline. Should the workflow require enhancement, the skill can be updated. Additionally, its memory retains useful facts and lessons learned from previous work.

Memory and skills serve distinct functions. Memory holds useful information and context, while skills store procedural methods for executing tasks. Together, they enable Hermes to build a comprehensive knowledge base covering both what it knows and how to perform recurring duties.

Automate work in the background

Hermes includes a built-in scheduler for recurring tasks. You can define schedules in natural language, allowing Hermes to perform work without waiting for you to initiate a new session.

This feature is ideal for reports, monitoring, backups, research, and other routines. Scheduled tasks also maintain continuity between runs, enabling 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 offers 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 may install the desktop application or use the command-line version independently.

For 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, launch the setup wizard to configure your model provider and other options:

hermes setup

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

Run Hermes on DaDesktop

Hermes requires an environment where it can execute tools and retain 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 advantageous when the model you wish to run requires more VRAM than your local machine possesses. 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.

Learn more about running local LLMs on DaDesktop.