Skip to content

lingxixueying/nodeskclaw

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

144 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

中文

DeskClaw

Your AI workforce, orchestrated. Deploy, manage, and scale AI agents on Kubernetes -- from a single pane of glass.

DeskClaw is a visual orchestration platform for AI employees. It organizes multiple AI Agents into collaborative teams through Cyber Workspaces, equips them with a Gene capability system, and enables one-click deployment, real-time monitoring, and elastic scaling on K8s clusters.

Highlights

  • Cyber Workspace -- Hexagonal topology workspace where AI employees auto-collaborate, share a blackboard, and publish tasks
  • Gene System -- Modular capability marketplace for hot-loading skills onto Agents, with support for private enterprise genes
  • One-Click Deploy -- End-to-end visual deployment pipeline with SSE real-time progress streaming
  • Multi-Cluster Management -- Cross-cluster instance orchestration, health checks, and elastic scaling
  • Feishu SSO -- Enterprise-grade authentication with automatic org structure sync

CE / EE

Dual-edition architecture: Community Edition / Enterprise Edition.

CE (Community) EE (Enterprise)
License Apache 2.0 Commercial
Features Instance deploy, cluster management, log monitoring, gene marketplace All of CE + multi-org, billing, advanced audit
Code This repository Private ee/ directory

Runtime auto-detection via FeatureGate -- if ee/ exists it runs as EE, otherwise CE. Feature registry defined in features.yaml.

Technical implementation: Backend Factory abstraction + Hook event bus; Frontend Stub + Vite Alias Override.

Architecture

DeskClaw/
├── nodeskclaw-portal/             # User Portal -- Vue 3 + Tailwind CSS
├── nodeskclaw-frontend/           # Admin Console -- Vue 3 + shadcn-vue + Tailwind CSS
├── nodeskclaw-backend/            # API Server -- Python 3.12 + FastAPI + SQLAlchemy
├── nodeskclaw-llm-proxy/          # LLM Proxy -- Go
├── nodeskclaw-artifacts/          # Docker images & deploy manifests
├── openclaw-channel-nodeskclaw/   # Workspace Agent channel plugin
├── features.yaml                  # CE/EE feature registry
├── ee/                            # Enterprise Edition (private)
├── openclaw/                      # DeskClaw runtime source (external)
└── vibecraft/                     # VibeCraft source (external)

i18n

Full-stack internationalization covering Portal, Admin, and Backend.

  • Language detection: zh* -> zh-CN, en* -> en-US, fallback en-US
  • Error display: prefer message_key local translation, fall back to message when missing
  • Backend contract: code + error_code + message_key + message + data

Quick Start

Prerequisites

Dependency
Python >= 3.12 + uv Backend runtime & package manager
Node.js >= 18 + npm Frontend runtime
PostgreSQL Database
Feishu App SSO (App ID + App Secret)

1. Configure

cd nodeskclaw-backend
cp .env.example .env
# Edit .env -- fill in the required values below
Variable Description
DATABASE_URL postgresql+asyncpg://user:pass@host:5432/dbname
JWT_SECRET JWT signing key
ENCRYPTION_KEY KubeConfig AES key (32-byte base64)
FEISHU_APP_ID Feishu App ID
FEISHU_APP_SECRET Feishu App Secret
FEISHU_REDIRECT_URI http://localhost:5173/api/v1/auth/feishu/callback

2. Backend

cd nodeskclaw-backend
uv sync
uv run uvicorn app.main:app --reload --port 8000

API at http://localhost:8000 | Swagger at http://localhost:8000/docs | Auto-migration on first boot.

3. Frontend

cd nodeskclaw-frontend
npm install && npm run dev

Portal at http://localhost:5173 | /api and /stream auto-proxy to backend.

4. Go

Open http://localhost:5173, sign in with Feishu.

Feishu redirect URL: http://localhost:5173/api/v1/auth/feishu/callback

Documentation

Backend API overview, directory layout, env vars
Artifacts DeskClaw image build & Dockerfile
Channel Plugin Workspace agent collaboration plugin

Contributing

PRs welcome. See CONTRIBUTING.md for guidelines.

License

Apache License 2.0

About

No description, website, or topics provided.

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 43.7%
  • Vue 41.3%
  • TypeScript 13.4%
  • Shell 1.1%
  • CSS 0.3%
  • Dockerfile 0.2%