hermes-hudui

Name: hermes-hudui
Rating: 76 (1 reviews)
Author: joeynyc

joeynyc/hermes-hudui

Hermes HUD Web UI is a browser-based dashboard for monitoring and interacting with the Hermes AI agent across 19 comprehensive tabs.

1.8k 225MITUpdated 2026-08-11

Great

View on GitHub Open source file

Overview

Hermes HUD Web UI provides a feature-rich, browser-based management interface for the Hermes AI agent. Built with a FastAPI Python backend and a React/Vite/Tailwind frontend, it reads agent telemetry directly from the local filesystem to display real-time metrics on memory, skills, sessions, costs, cron jobs, and sudo governance. It includes built-in live chat, multiple themes, command palette navigation, and artifact export capabilities for run replays.

Capabilities

▸Real-time monitoring across 19 dashboard tabs via WebSockets
▸Live chat integration with Hermes agent subprocesses
▸Persistent memory CRUD operations with file-locking support
▸Cost and token analytics per model and session
▸Safe-share run replay generation with redaction and local signing
▸Theme customization and command palette navigation

Best for

Monitoring AI agent operational health and token costs in real time, Managing persistent agent memory and inspecting learned skills, Streaming live chat interactions and reviewing past session timelines, Exporting redacted run replays as shareable markdown, HTML, or JSON artifacts

Works with

Codex

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%33 → +4.0

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%84 → +6.7

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%25 → +1.3

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total76.4 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

The server runs locally by default, rejecting untrusted origins and non-loopback connections. Exposing it externally requires configuring explicit trusted hosts, origin parameters, TLS, and proper authentication layers.