AgentDeck
puritysb/AgentDeck
AgentDeck integrates AI coding agents with physical control surfaces and hardware displays, allowing users to monitor and steer multiple active coding sessions in real time.
194 37MITUpdated 2026-08-13
81
GreatOverview
AgentDeck acts as a unified hub and daemon system for tracking AI coding agents like Claude Code, Codex, and OpenCode. It bridges agent lifecycle events to dozens of peripheral hardware surfaces including Stream Decks, e-ink readers, Android tablets, ESP32 panels, and terminal dashboards, giving developers visual state indicators, quota gauges, and tactile controls without needing to constantly stare at terminal windows.
Capabilities
- ▸Tracks AI coding agent sessions (Claude Code, Codex, OpenCode)
- ▸Drives multiple hardware control surfaces including Stream Decks, Ulanzi panels, and e-ink displays
- ▸Provides a rich terminal TUI dashboard with live telemetry and braille visualizations
- ▸Supports cross-machine remote session attachment over a local network
- ▸Captures and synchronizes agent state using native lifecycle hooks
Best for
Monitoring multiple concurrent AI coding sessions across different projects from a physical Stream Deck or hardware display, Tracking usage quotas and rate limits in real time via dedicated physical or terminal gauges, Quickly jumping into waiting or idle agent sessions with a single physical button press
Works with
Claude CodeCodexOpenCode
Evoa Score breakdown= Σ (score × weight)
81Task usefulness20%88 → +17.6
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%40 → +4.8
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%80 → +12.0
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%95 → +9.5
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%61 → +4.9
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
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 total81.0 / 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 application listens locally and handles agent telemetry. Remote daemon attachment uses standard TCP sockets and requires explicit user configuration.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.