nesquena

hermes-webui

// summary

Hermes WebUI provides a lightweight, dark-themed browser interface that offers full parity with the Hermes Agent CLI. It features a three-panel layout for chat, file management, and session navigation without requiring complex build steps or frameworks. Users can securely access their self-hosted agent via SSH tunnels or mobile devices while maintaining persistent memory and cross-session context.

// technical analysis

Hermes Web UI is a lightweight, dark-themed browser interface designed to provide full parity with the Hermes Agent CLI, enabling users to manage autonomous agents directly from a web browser. By utilizing a three-panel layout and a composer footer, the project prioritizes accessibility and context awareness, allowing users to manage sessions, workspace files, and model configurations without complex build steps or frameworks. The architecture relies on vanilla JavaScript and Python, ensuring a seamless integration with existing Hermes agent setups while maintaining a focus on self-hosted, persistent, and provider-agnostic agentic workflows.

// key highlights

Provides 1:1 feature parity with the Hermes CLI, allowing users to manage agents, sessions, and workspace files entirely through a web browser.

Features a responsive three-panel layout that includes a session sidebar, a central chat interface, and a workspace file browser with inline previews.

Supports multi-provider model integration, allowing users to switch between OpenAI, Anthropic, Google, DeepSeek, and others via a dynamic dropdown.

Includes a robust workspace management system that supports file editing, directory navigation, and Git status tracking directly within the UI.

Offers advanced agent interaction tools, such as inline tool call cards, subagent delegation visualization, and Mermaid diagram rendering.

Ensures secure, self-hosted operation with optional password protection and support for remote access via SSH tunnels or Tailscale.

// use cases

Persistent cross-session AI agent management with self-improving skills

Self-hosted scheduling of cron jobs that deliver results to messaging platforms

Integrated workspace file browsing with inline editing and syntax highlighting

// getting started

To begin, clone the repository and run the bootstrap script using 'python3 bootstrap.py', which automatically detects your Hermes Agent, sets up the Python environment, and launches the web server. Alternatively, you can use the provided Docker Compose files to deploy the Web UI alongside your agent in a containerized environment. Once running, access the interface at http://localhost:8787 or via an SSH tunnel if hosting on a remote server.