joeynyc/hermes-hudui

Web UI consciousness monitor for Hermes — the AI agent with persistent memory

What it solves

It provides a visual monitoring and management interface for the Hermes AI agent, allowing users to inspect the agent's internal state, memory, and performance without relying solely on a command-line interface.

How it works

The HUD reads data directly from the agent's local storage directory (~/.hermes/) and communicates with the hermes CLI. It uses WebSockets for real-time updates and native filesystem events to track changes to the agent's on-disk layout. The server is local-only by default for security.

Who it’s for

Users of the Hermes AI agent who want a comprehensive dashboard to track their agent's "consciousness," manage plugins, and analyze model costs and performance.

Highlights

  • Comprehensive Monitoring: 19 tabs covering identity, memory, skills, sessions, costs, and model analytics.
  • Hermes Replay: A tool to create redacted, shareable proof artifacts of agent runs in formats like JSON, Markdown, and HTML.
  • Gateway Visibility: Tracking of managed-tool routing for web search, image generation, and browser automation.
  • Plugin Hub: A centralized place to enable, disable, and update dashboard and agent plugins.
  • Real-time Updates: Live data synchronization via WebSockets and a command palette for quick navigation.

Related

  • Project
    sharbelxyz/hermes-agent-mission-control

    A self-hostable dashboard template that acts as a mission control center for the Hermes AI agent, allowing users to dispatch tasks and manage memory via a shared Postgres database.

  • Project
    abundantbeing/hermes-browser-extension

    A Chromium side‑panel extension that connects your browser to a Hermes Agent (local, cloud, or remote). It streams active‑tab context, supports multi‑agent switching, smart tab scoping, site‑aware drafting (Hermes Assist), page comments, and optional live tab control, all with transparent diagnostics and nine visual themes.

  • Project
    EKKOLearnAI/hermes-studio

    A multi-agent desktop app and web console that provides a unified workspace for running and orchestrating agents like Hermes, Ekko, and Claude Code.

  • Project
    outsourc-e/hermes-workspace

    A comprehensive command center for AI agents that integrates chat, memory, skills, and a terminal into a single workspace for orchestrating multi-agent swarms.

  • Project
    VasiHemanth/tokentelemetry

    A local observability dashboard that tracks token usage, LLM costs, and session traces for AI coding and autonomous agents by reading their local log files.