hermes-webui: a lightweight web interface providing full CLI parity for the autonomous Hermes Agent

What it solves

Hermes Web UI provides a graphical browser interface for the Hermes Agent, removing the need to interact with the autonomous agent solely through a terminal or messaging apps. It bridges the gap between a powerful CLI-based agent and a user-friendly web experience, offering 1:1 parity with the CLI's capabilities.

How it works

It is a lightweight web application built with Python and vanilla JavaScript (no frameworks or bundlers) that runs on your server. It integrates directly with your existing Hermes agent setup and models. Users can access it securely via an SSH tunnel. The UI is organized into a three-panel layout: a left sidebar for session management, a center chat area, and a right workspace for file browsing.

Who it’s for

Users of the Hermes Agent who prefer a visual interface for managing conversations, browsing workspace files, and configuring agent profiles and tasks without leaving their browser.

Highlights

• Full CLI Parity: Access everything available in the Hermes CLI from the browser.
• Workspace File Browser: A built-in directory tree with inline previews for text, code, and images, supporting file editing and Git detection.
• Session Management: Organize conversations with projects, tags, pinning, and archiving, with the ability to import sessions from the CLI.
• Agent Control: Manage persistent memory, self-improving skills, and self-hosted cron jobs (Tasks) through dedicated panels.
• Multi-Provider Support: Compatible with various LLM providers including OpenAI, Anthropic, Google, DeepSeek, and local endpoints like Ollama.
• Security: Supports optional password authentication and passkeys (WebAuthn) for secure access.