Hermes WebUI: A Powerful Web Interface for Your Autonomous AI Agent

Summary

Hermes WebUI provides a lightweight, dark-themed web application for interacting with Hermes Agent, offering full parity with the CLI experience. This self-hosted interface allows users to manage sessions, browse workspaces, and control their AI agent from any web browser or phone, enhancing accessibility and user experience. It integrates seamlessly with existing Hermes Agent setups, requiring no additional configuration.

Use at your own risk

OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.

Introduction

Hermes WebUI is a sophisticated web application designed to provide a user-friendly interface for the powerful Hermes Agent. This lightweight, dark-themed web app offers full parity with the command-line interface, allowing users to manage their autonomous AI agent from a web browser or mobile device. Built with Python and vanilla JavaScript, it emphasizes simplicity, requiring no complex build steps or frameworks.

Installation

Getting started with Hermes WebUI is straightforward. First, clone the repository and run the bootstrap script:

git clone https://github.com/nesquena/hermes-webui.git hermes-webui
cd hermes-webui
python3 bootstrap.py

Alternatively, you can use the start.sh script:

./start.sh

For self-hosted VM or homelab installations, ctl.sh provides daemon lifecycle commands:

./ctl.sh start

Docker deployments are also supported with pre-built images available on GHCR, offering single or multi-container setups. Refer to the official Docker documentation for detailed instructions.

Examples

The Hermes WebUI features an intuitive three-panel layout: a left sidebar for sessions and navigation, a central chat area, and a right panel for workspace file browsing. Key controls for models, profiles, and workspaces are conveniently located in the composer footer, always visible during interaction. A circular context ring provides a quick glance at token usage, while all settings and session tools are accessible via the Hermes Control Center. The interface supports both dark and light modes, offers inline preview for workspace files, and includes rich features like tool call cards, subagent delegation, and Mermaid diagram rendering.

Why use Hermes WebUI?

Hermes WebUI stands out by providing a persistent, self-hosted, and highly capable AI agent experience. Unlike many AI tools that reset context with each session, Hermes retains memory, learns your environment, and runs scheduled jobs even when you're offline. It supports over 10 messaging platforms, allowing access from various devices. The agent itself is self-improving, automatically writing and saving its own skills, and is provider-agnostic, working with OpenAI, Anthropic, Google, and more. By using Hermes WebUI, you gain a powerful, private, and customizable AI assistant that truly gets smarter over time, all from a convenient web interface.