feat: add hermes runtime integration

.gitignore

@@ -57,6 +57,8 @@ Thumbs.db
 *.temp
 /test_*
 
+
+.codex-logs/
 dev_docs/
 devplan.md
 AGENTS.md

README.de.md

@@ -29,6 +29,7 @@
   <a href="#product-tour">Produktueberblick</a> |
   <a href="#ai-gateway">AI Gateway</a> |
   <a href="#agent-control-plane">Agent Control Plane</a> |
+  <a href="#runtime-integrations">Runtime-Integrationen</a> |
   <a href="#resource-management">Ressourcenverwaltung</a> |
   <a href="#get-started">Erste Schritte</a>
 </p>
@@ -53,6 +54,7 @@
 
 Wichtige aktuelle Produkt- und Dokumentations-Updates.
 
+- [2026-04-29] Hermes-Runtime-Integration hinzugefuegt, inklusive Webtop-basierter Instanzbereitstellung, Agent-Control-Plane-Registrierung, AI-Gateway-Injection, channel- und skill-Bootstrap sowie `.hermes` Import/Export. Siehe [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md).
 - [2026-04-08] Skill-Verwaltung und Skill-Scanning wurden der Plattform hinzugefuegt. Details siehe [Merged PR #52](https://github.com/Yuan-lab-LLM/ClawManager/pull/52).
 - [2026-03-26] Die AI-Gateway-Dokumentation wurde erweitert und deckt nun Modell-Governance, Audit und Trace, Kostenrechnung sowie Risikokontrolle genauer ab. Siehe [AI Gateway Guide](./docs/aigateway.md).
 - [2026-03-20] ClawManager hat sich zu einer breiteren Control Plane fuer AI-Agent-Workspaces entwickelt, mit staerkerer Runtime-Steuerung, wiederverwendbaren Ressourcen und Security-Scanning-Workflows.
@@ -84,6 +86,21 @@ Es eignet sich besonders fuer:
 - Betriebsteams, die Runtime-Sichtbarkeit, Command-Dispatch und Desired-State-Kontrolle benoetigen
 - Entwicklungsteams, die Agent-Workspaces ueber wiederverwendbare Ressourcen statt ueber manuelle Konfiguration bereitstellen wollen
 
+<a id="runtime-integrations"></a>
+## Runtime-Integrationen
+
+ClawManager unterstuetzt jetzt OpenClaw und Hermes als verwaltete Runtime-Integrationen. Hermes wird auf der Webtop-Basis integriert: Desktop-Zugriff laeuft ueber Port `3001`, persistente Daten liegen unter `/config/.hermes`, und der eingebettete Hermes agent verbindet sich mit ClawManager, um Runtime-Status, Health, Metriken, Commands, channel-Injection, skill-Injection und Skill-Package-Synchronisierung zu verarbeiten.
+
+Hermes-Instanzen erhalten die gleichen plattformverwalteten Faehigkeiten wie OpenClaw-artige Workspaces:
+
+- AI-Gateway-Injection ueber OpenAI-kompatible Umgebungsvariablen
+- Agent-Bootstrap und sessionbasierte Registrierung
+- channel- und skill-Bootstrap-Payloads fuer Runtime-seitige Konfiguration
+- `install_skill`, `collect_skill_package`, Health-Check- und System-Info-Commands
+- `.hermes` Workspace-Import und -Export fuer persistente Runtime-Daten
+
+Runtime-Autoren koennen dem [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md), dem [Generic Runtime Agent Integration Guide](./docs/runtime-agent-integration-guide.md) und der [Skill Content MD5 Spec](./docs/skill-content-md5-spec.md) folgen, um kompatible Agents zu bauen.
+
 <a id="get-started"></a>
 ## Erste Schritte
 
@@ -191,6 +208,9 @@ Siehe [Developer Guide (English)](./docs/developer-guide.md).
 - [AI Gateway Guide (English)](./docs/aigateway.md)
 - [Security / Skill Scanner Guide (English)](./docs/security-skill-scanner.md)
 - [Resource Management Guide (English)](./docs/resource-management.md)
+- [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)
+- [Generic Runtime Agent Integration Guide](./docs/runtime-agent-integration-guide.md)
+- [Skill Content MD5 Spec](./docs/skill-content-md5-spec.md)
 - [Developer Guide (English)](./docs/developer-guide.md)
 
 ## Lizenz

README.ja.md

@@ -29,6 +29,7 @@
   <a href="#product-tour">製品紹介</a> |
   <a href="#ai-gateway">AI Gateway</a> |
   <a href="#agent-control-plane">Agent Control Plane</a> |
+  <a href="#runtime-integrations">Runtime 連携</a> |
   <a href="#resource-management">リソース管理</a> |
   <a href="#get-started">はじめに</a>
 </p>
@@ -53,6 +54,7 @@
 
 最近の重要な製品アップデートとドキュメント更新です。
 
+- [2026-04-29] Hermes Runtime 連携を追加しました。Webtop ベースのインスタンス作成、Agent Control Plane 登録、AI Gateway 注入、channel と skill のブートストラップ、`.hermes` のインポート/エクスポートに対応しています。詳しくは [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md) を参照してください。
 - [2026-04-08] プラットフォームに Skill 管理と Skill スキャンのワークフローを追加しました。詳細は [Merged PR #52](https://github.com/Yuan-lab-LLM/ClawManager/pull/52) を参照してください。
 - [2026-03-26] AI Gateway ドキュメントを更新し、モデルガバナンス、監査とトレース、コスト計算、リスク制御の説明を強化しました。詳しくは [AI Gateway Guide](./docs/aigateway.md) を参照してください。
 - [2026-03-20] ClawManager は、AI エージェントワークスペース向けのより広いコントロールプレーンへと進化し、ランタイム制御、再利用可能なリソース、安全スキャンのワークフローを強化しました。
@@ -84,6 +86,21 @@ ClawManager は、AI エージェントインスタンスの運用を Kubernetes
 - ランタイムの可観測性、コマンド配布、 desired state 管理が必要な運用チーム
 - 手作業の設定ではなく、再利用可能なリソースで Agent ワークスペースを届けたい開発チーム
 
+<a id="runtime-integrations"></a>
+## Runtime 連携
+
+ClawManager は、OpenClaw と Hermes の両方を管理対象 Runtime としてサポートします。Hermes は Webtop ベースラインで統合されます。デスクトップアクセスは `3001` ポートを使い、永続データは `/config/.hermes` に保存され、内蔵 Hermes agent が ClawManager に接続してランタイム状態、ヘルス、メトリクスを報告し、コマンド、channel 注入、skill 注入、skill パッケージ同期を処理します。
+
+Hermes インスタンスでは、OpenClaw スタイルのワークスペースと同じプラットフォーム管理機能を利用できます。
+
+- OpenAI 互換環境変数による AI Gateway 注入
+- bootstrap token と session token による Agent 登録
+- Runtime 側設定向けの channel と skill ブートストラップ payload
+- `install_skill`、`collect_skill_package`、ヘルスチェック、システム情報収集コマンド
+- 永続 Runtime データを移行するための `.hermes` ワークスペースのインポート/エクスポート
+
+Runtime 開発者は、[Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)、[Generic Runtime Agent Integration Guide](./docs/runtime-agent-integration-guide.md)、[Skill Content MD5 Spec](./docs/skill-content-md5-spec.md) を参照して互換 agent を実装できます。
+
 <a id="get-started"></a>
 ## はじめに
 
@@ -191,6 +208,9 @@ ClawManager は、React フロントエンド、Go バックエンド、状態
 - [AI Gateway Guide (English)](./docs/aigateway.md)
 - [Security / Skill Scanner Guide (English)](./docs/security-skill-scanner.md)
 - [Resource Management Guide (English)](./docs/resource-management.md)
+- [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)
+- [Generic Runtime Agent Integration Guide](./docs/runtime-agent-integration-guide.md)
+- [Skill Content MD5 Spec](./docs/skill-content-md5-spec.md)
 - [Developer Guide (English)](./docs/developer-guide.md)
 
 ## ライセンス

README.ko.md

@@ -29,6 +29,7 @@
   <a href="#product-tour">제품 소개</a> |
   <a href="#ai-gateway">AI Gateway</a> |
   <a href="#agent-control-plane">Agent Control Plane</a> |
+  <a href="#runtime-integrations">Runtime 연동</a> |
   <a href="#resource-management">리소스 관리</a> |
   <a href="#get-started">시작하기</a>
 </p>
@@ -53,6 +54,7 @@
 
 최근의 중요한 제품 및 문서 업데이트입니다.
 
+- [2026-04-29] Hermes Runtime 연동을 추가했습니다. Webtop 기반 인스턴스 생성, Agent Control Plane 등록, AI Gateway 주입, channel 및 skill 부트스트랩, `.hermes` 가져오기/내보내기 흐름을 지원합니다. 자세한 내용은 [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)를 참고하세요.
 - [2026-04-08] 플랫폼에 Skill 관리와 Skill 스캔 워크플로우가 추가되었습니다. 자세한 내용은 [Merged PR #52](https://github.com/Yuan-lab-LLM/ClawManager/pull/52)를 참고하세요.
 - [2026-03-26] AI Gateway 문서를 업데이트하여 모델 거버넌스, 감사와 추적, 비용 계산, 리스크 제어 설명을 강화했습니다. 자세한 내용은 [AI Gateway Guide](./docs/aigateway.md)를 참고하세요.
 - [2026-03-20] ClawManager는 AI Agent 워크스페이스를 위한 더 넓은 컨트롤 플레인으로 발전했으며, 런타임 제어, 재사용 가능한 리소스, 보안 스캔 워크플로우가 강화되었습니다.
@@ -84,6 +86,21 @@ ClawManager는 AI Agent 인스턴스 운영을 Kubernetes 위로 확장하고, 
 - 런타임 가시성, 명령 배포, desired state 제어가 필요한 운영 팀
 - 수동 설정 대신 재사용 가능한 리소스로 Agent 워크스페이스를 제공하고 싶은 개발 팀
 
+<a id="runtime-integrations"></a>
+## Runtime 연동
+
+ClawManager는 이제 OpenClaw와 Hermes를 모두 관리형 Runtime 연동으로 지원합니다. Hermes는 Webtop 기준으로 통합됩니다. 데스크톱 접근은 `3001` 포트를 사용하고, 영구 데이터는 `/config/.hermes`에 저장되며, 내장 Hermes agent가 ClawManager에 연결해 런타임 상태, 헬스, 메트릭을 보고하고 명령, channel 주입, skill 주입, skill 패키지 동기화를 처리합니다.
+
+Hermes 인스턴스는 OpenClaw 스타일 워크스페이스와 동일한 플랫폼 관리 기능을 사용할 수 있습니다.
+
+- OpenAI 호환 환경 변수를 통한 AI Gateway 주입
+- bootstrap token 및 session token 기반 Agent 등록
+- Runtime 측 설정을 위한 channel 및 skill 부트스트랩 payload
+- `install_skill`, `collect_skill_package`, 헬스 체크, 시스템 정보 수집 명령
+- 영구 Runtime 데이터 이전을 위한 `.hermes` 워크스페이스 가져오기/내보내기
+
+Runtime 개발자는 [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md), [Generic Runtime Agent Integration Guide](./docs/runtime-agent-integration-guide.md), [Skill Content MD5 Spec](./docs/skill-content-md5-spec.md)를 참고해 호환 agent를 구현할 수 있습니다.
+
 <a id="get-started"></a>
 ## 시작하기
 
@@ -191,6 +208,9 @@ ClawManager는 React 프런트엔드, Go 백엔드, 상태 저장용 MySQL, 그
 - [AI Gateway Guide (English)](./docs/aigateway.md)
 - [Security / Skill Scanner Guide (English)](./docs/security-skill-scanner.md)
 - [Resource Management Guide (English)](./docs/resource-management.md)
+- [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)
+- [Generic Runtime Agent Integration Guide](./docs/runtime-agent-integration-guide.md)
+- [Skill Content MD5 Spec](./docs/skill-content-md5-spec.md)
 - [Developer Guide (English)](./docs/developer-guide.md)
 
 ## 라이선스

README.md

@@ -29,6 +29,7 @@
   <a href="#product-tour">Explore the Product</a> |
   <a href="#ai-gateway">AI Gateway</a> |
   <a href="#agent-control-plane">Agent Control Plane</a> |
+  <a href="#runtime-integrations">Runtime Integrations</a> |
   <a href="#resource-management">Resource Management</a> |
   <a href="#get-started">Get Started</a>
 </p>
@@ -53,6 +54,7 @@
 
 Recent highlights from the latest product and documentation updates.
 
+- [2026-04-29] Added Hermes runtime integration support, including Webtop-based instance provisioning, Agent Control Plane registration, AI Gateway injection, channel and skill bootstrap, and `.hermes` import/export workflows. See the [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md).
 - [2026-04-08] Added skill management and skill scanning workflows to the platform, via [Merged PR #52](https://github.com/Yuan-lab-LLM/ClawManager/pull/52).
 - [2026-03-26] AI Gateway documentation was refreshed with stronger coverage for model governance, audit and trace, cost accounting, and risk control. See the [AI Gateway Guide](./docs/aigateway.md).
 - [2026-03-20] ClawManager evolved into a broader control plane for AI agent workspaces, with stronger runtime control, reusable resources, and security scanning workflows.
@@ -84,6 +86,21 @@ It is designed for:
 - operators who need runtime visibility, command dispatch, and desired-state control
 - builders who want governed AI access and reusable resource injection instead of manual per-instance setup
 
+<a id="runtime-integrations"></a>
+## Runtime Integrations
+
+ClawManager now supports both OpenClaw and Hermes as managed runtime integrations. Hermes is integrated on the Webtop baseline: desktop access uses port `3001`, persistent data lives under `/config/.hermes`, and the embedded Hermes agent connects back to ClawManager for runtime status, health, metrics, commands, channel injection, skill injection, and skill package synchronization.
+
+Hermes instances receive the same platform-managed capabilities as OpenClaw-style workspaces:
+
+- AI Gateway environment injection through OpenAI-compatible variables
+- Agent bootstrap and session-based registration
+- channel and skill bootstrap payloads for runtime-side configuration
+- `install_skill`, `collect_skill_package`, health check, and system info commands
+- `.hermes` workspace import and export for persistent runtime data
+
+Runtime authors can follow the [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md), the [Generic Runtime Agent Integration Guide](./docs/runtime-agent-integration-guide.md), and the [Skill Content MD5 Spec](./docs/skill-content-md5-spec.md) to build compatible agents.
+
 ## Get Started
 
 ClawManager now has clearer entry points for both full Kubernetes deployments and lightweight cluster setups. If you want to evaluate the product quickly, start with the guide that matches your environment and then follow the first-use walkthrough.
@@ -187,6 +204,9 @@ See the [Developer Guide](./docs/developer-guide.md).
 - [AI Gateway Guide](./docs/aigateway.md)
 - [Security / Skill Scanner Guide](./docs/security-skill-scanner.md)
 - [Resource Management Guide](./docs/resource-management.md)
+- [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)
+- [Generic Runtime Agent Integration Guide](./docs/runtime-agent-integration-guide.md)
+- [Skill Content MD5 Spec](./docs/skill-content-md5-spec.md)
 - [Developer Guide](./docs/developer-guide.md)
 
 ## License

README.zh-CN.md

@@ -29,6 +29,7 @@
   <a href="#product-tour">了解产品</a> |
   <a href="#ai-gateway">AI Gateway</a> |
   <a href="#agent-control-plane">Agent Control Plane</a> |
+  <a href="#runtime-integrations">Runtime 接入</a> |
   <a href="#resource-management">资源管理</a> |
   <a href="#get-started">快速开始</a>
 </p>
@@ -53,6 +54,7 @@
 
 这里展示最近的重要产品与文档更新。
 
+- [2026-04-29] 新增 Hermes Runtime 接入支持，覆盖基于 Webtop 的实例创建、Agent Control Plane 注册、AI Gateway 注入、channel 与 skill 引导注入，以及 `.hermes` 导入导出流程。见 [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)。
 - [2026-04-08] 平台新增了 Skill 管理与 Skill 扫描工作流，见 [Merged PR #52](https://github.com/Yuan-lab-LLM/ClawManager/pull/52)。
 - [2026-03-26] AI Gateway 文档已更新，补充了模型治理、审计追踪、成本核算与风险控制能力，见 [AI Gateway Guide](./docs/aigateway.md)。
 - [2026-03-20] ClawManager 进一步演进为面向 AI Agent 工作空间的控制平面，强化了运行时控制、可复用资源与安全扫描工作流。
@@ -84,6 +86,21 @@ ClawManager 将 AI Agent 实例的运行、治理与运维能力带到 Kubernete
 - 需要运行时可观测性、命令下发与期望态控制的运维团队
 - 希望以可复用资源而不是手工配置方式交付 Agent 工作空间的开发团队
 
+<a id="runtime-integrations"></a>
+## Runtime 接入
+
+ClawManager 现在同时支持 OpenClaw 与 Hermes 作为受管 Runtime 接入。Hermes 按 Webtop 基线集成：桌面访问使用 `3001` 端口，持久化数据目录为 `/config/.hermes`，镜像内置的 Hermes agent 回连 ClawManager，上报运行时状态、健康信息、监测数据，并接收命令、channel 注入、skill 注入与 skill 包同步。
+
+Hermes 实例可以获得与 OpenClaw 风格工作空间一致的平台能力：
+
+- 通过 OpenAI 兼容环境变量注入 AI Gateway
+- 基于 bootstrap token 与 session token 的 Agent 注册
+- 用于 Runtime 侧配置的 channel 与 skill 引导 payload
+- `install_skill`、`collect_skill_package`、健康检查与系统信息采集命令
+- `.hermes` 工作空间导入导出，用于持久化 Runtime 数据迁移
+
+Runtime 开发方可以参考 [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)、[通用 Runtime Agent 接入指南](./docs/runtime-agent-integration-guide.md) 与 [Skill Content MD5 规范](./docs/skill-content-md5-spec.md) 实现兼容 agent。
+
 <a id="get-started"></a>
 ## 快速开始
 
@@ -191,6 +208,9 @@ ClawManager 是一个 Kubernetes 原生平台，包含 React 前端、Go 后端
 - [AI Gateway Guide（英文）](./docs/aigateway.md)
 - [Security / Skill Scanner Guide（英文）](./docs/security-skill-scanner.md)
 - [Resource Management Guide（英文）](./docs/resource-management.md)
+- [Hermes Runtime Guide](./docs/hermes-runtime-agent-development.md)
+- [通用 Runtime Agent 接入指南](./docs/runtime-agent-integration-guide.md)
+- [Skill Content MD5 规范](./docs/skill-content-md5-spec.md)
 - [Developer Guide（英文）](./docs/developer-guide.md)
 
 ## 许可证

backend/cmd/server/main.go

@@ -199,6 +199,8 @@ func main() {
 			instances.POST("/:id/sync", instanceHandler.ForceSync)
 			instances.GET("/:id/openclaw/export", instanceHandler.ExportOpenClaw)
 			instances.POST("/:id/openclaw/import", instanceHandler.ImportOpenClaw)
+			instances.GET("/:id/hermes/export", instanceHandler.ExportHermes)
+			instances.POST("/:id/hermes/import", instanceHandler.ImportHermes)
 			instances.GET("/:id/skills", skillHandler.ListInstanceSkills)
 			instances.POST("/:id/skills", skillHandler.AttachSkillToInstance)
 			instances.DELETE("/:id/skills/:skillId", skillHandler.RemoveSkillFromInstance)