nesquena/hermes-webui
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
What it solves
Hermes WebUI provides a graphical browser interface for the Hermes Agent, an autonomous AI agent that runs on a server. It eliminates the need to interact with the agent solely via a terminal (CLI) or messaging apps, offering a full-featured web-based workspace for managing AI conversations, files, and agent configurations.
How it works
Built with Python and vanilla JavaScript (no heavy frameworks or bundlers), the WebUI acts as a frontend for the existing Hermes Agent setup. It runs as a lightweight server that can be accessed securely via SSH tunnels. The interface is organized into a three-panel layout: a sidebar for session management, a center chat area, and a right-side workspace for file browsing and editing. It integrates directly with the Hermes agent's memory, profiles, and skill systems.
Who it’s for
Users who already use or want to use the Hermes Agent but prefer a visual interface over a CLI, as well as developers and power users who want to manage their self-hosted AI agent's files, cron jobs, and multi-provider model settings from any device.
Highlights
- Full CLI Parity: Every action available in the terminal is accessible via the web interface.
- Integrated Workspace: A built-in file browser with inline previews, editing capabilities, and Git detection.
- Session Management: Advanced organization using projects, tags, pinning, and archiving, with the ability to import/export transcripts.
- Agent Visibility: Visual cards for tool calls, subagent delegation, and reasoning blocks (e.g., Claude thinking or o3 reasoning).
- Comprehensive Control: Management of multiple AI profiles, provider-agnostic model switching, and a dedicated "Control Center" for system settings.
- Security: Supports optional password authentication, passkeys (WebAuthn), and OIDC login.
Related
- Project
- Project
- Project
- Project
- Project