Nous Research presented Hermes Agent profile builder

On June 11, 2026, Nous Research released an update to the Hermes Agent dashboard — a constructor for AI agent profiles that for the first time unified the selection of identity, model, skills, and MCP servers into a single step-by-step flow within the web interface. Previously, configuring an agent required multi-step work through the command line (CLI), which was a noticeable barrier to entry for users without a technical background.

What Changed in the Interface

Previously, assembling an agent on the Hermes Agent platform required sequential actions in the terminal: agent identity was set separately, the model was selected separately, skills and MCP servers were connected separately. The new dashboard flow consolidates all these steps into one form — a user goes through the configuration once and receives a ready-made agent profile without switching between commands and configuration files.

• Company: Nous Research
• Product: Hermes Agent (dashboard/panel update)
• What's new: unified flow for identity, model, skills, and MCP servers
• What it replaces: multi-step configuration via CLI
• Announcement date: June 11, 2026 (according to MarkTechPost)

Why MCP Servers Matter for an Agent

MCP (Model Context Protocol) is an open protocol that allows AI models to safely connect to external tools, databases, and services instead of each developer writing their own integration from scratch. For agent platforms like Hermes Agent, this is a key component: through MCP servers, the agent gains access to the file system, third-party service APIs, or specialized tools, expanding the set of tasks it can perform autonomously. Including MCP server selection directly in the profile constructor means that users no longer need to manually write connection configuration — it becomes part of the wizard alongside model selection.

The other two components of the flow — identity and skills — also play non-decorative roles. Identity defines how the agent presents itself and on what persona or system prompt its behavior is built when communicating with users and other services. Skills, in turn, are modular sets of abilities that can be enabled and disabled as needed without rewriting the base agent configuration from scratch: much like how plugins extend program functionality without changing its core. Combining these three layers — who the agent is, what model drives it, and what it can do — in a single wizard frees the user from having to remember in which order and in which file each parameter is configured.

What This Means for Developers

Nous Research has long been known as a developer of open models from the Hermes family — fine-tunings based on large open-source LLMs, oriented toward follow-instruction behavior and function calling. A logical continuation of this line was the transition from "model as a product" to "agent as a product": instead of having the user assemble an agent around the Hermes model themselves, the company offers a ready-made visual constructor. For developers and small teams, this lowers the barrier to entry into creating autonomous AI agents — you don't need to know CLI command syntax or the structure of configuration files, just go through one flow in the browser.

The trend this update fits into is broader than one product: as the popularity of agent AI systems grows, platform developers are one by one transitioning from terminal tools to graphical interfaces, lowering the barrier to entry for non-programming audiences. Agent systems are gradually becoming a product not only for engineers but also for a wider audience for whom quickly assembling a working assistant without diving into infrastructure details matters.

At the same time, Nous Research itself has historically positioned itself as one of the notable players in the open (open-weight) segment of AI models rather than as a closed corporate laboratory, and continues this line of openness in tools for agent assembly. The dashboard combining identity, model, skills, and MCP servers logically complements the Hermes model lineup: now users not only have an open model but also a clear interface to wrap it in a working agent without having to understand the details of integrating with the MCP protocol or manually structuring configuration files.