WorkPilot-AI 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 8.5 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
WorkPilot-AI 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
WorkPilot-AI 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install workpilot-ai
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install workpilot-ai
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/tleub-ebp/WorkPilot-AI
cd WorkPilot-AI
pip install -e .
# 验证安装
python -c "import workpilot_ai; print('安装成功')"
# 命令行使用
workpilot-ai --help
# 基本用法
workpilot-ai input_file -o output_file
# Python 代码中调用
import workpilot_ai
# 示例
result = workpilot_ai.process("input")
print(result)
# workpilot-ai 配置文件示例(config.yml) app: name: "workpilot-ai" debug: false log_level: "INFO" # 运行时指定配置文件 workpilot-ai --config config.yml # 或通过环境变量配置 export WORKPILOT_AI_API_KEY="your-key" export WORKPILOT_AI_OUTPUT_DIR="./output"
Autonomous multi-agent coding framework that plans, builds, and validates software for you.

---
1. Téléchargement - Visitez GitHub Releases - Téléchargez la version stable pour votre plateforme
2. Installation - Windows : Exécutez WorkPilot-AI-1.0.0-win32-x64.exe - macOS : Ouvrez WorkPilot-AI-1.0.0-darwin-arm64.dmg - Linux : Lancez WorkPilot-AI-1.0.0-linux-x86_64.AppImage
3. Premier Lancement - Lancez l'application - Suivez l'assistant de configuration - Connectez votre provider AI
1. Clonage du Dépôt
git clone https://github.com/tleub-ebp/WorkPilot-AI.git
cd Auto-Claude_EBP
2. Installation Automatique
pnpm install
pnpm run dev
Crée automatiquement l'environnement virtuel Python et installe toutes les dépendances
3. Lancement Manuel
# Backend
cd apps/backend
python -m pip install -r requirements.txt
# Frontend
cd ../frontend
pnpm install
pnpm run dev
#### Tests de Connexion ```bash
Or from source:
pnpm install
pnpm run dev
See the Setup Guide for detailed instructions.
---
For headless operation, CI/CD integration, or terminal-only workflows:
cd apps/backend
python spec_runner.py --interactive # Create a spec interactively
python run.py --spec 001 # Run autonomous build
python run.py --spec 001 --review # Review
python run.py --spec 001 --merge # Merge
See docs/CLI-USAGE.md for the full CLI reference.
---
#### Authentification Claude (Recommandé) ```bash claude
AUTO_BUILD_MODEL=claude-3-5-sonnet-20241022 DEBUG=true LINEAR_API_KEY=votre_clé_linear GRAPHITI_ENABLED=true ```
#### Structure de Projet Requise
votre-projet/
├── .git/ # Obligatoire : dépôt Git initialisé
├── package.json # Pour projets Node.js
├── requirements.txt # Pour projets Python
├── Cargo.toml # Pour projets Rust
└── ... # Vos fichiers de code
#### Détection Automatique de Stack WorkPilot AI détecte automatiquement : - Framework : React, Vue, Angular, Django, Flask, Express - Language : TypeScript, JavaScript, Python, Rust, Go - Build Tools : Vite, Webpack, Cargo, Poetry - Testing : Jest, Pytest, Vitest, Playwright
claude --version ```
| Feature | Description |
|---|---|
| **Kanban Board** | Visual task management from planning through completion with real-time agent progress |
| **Multi-Agent Pipeline** | Planner → Coder → QA Reviewer → QA Fixer pipeline runs autonomously end-to-end |
| **Parallel Execution** | Up to 12 simultaneous agent terminals for parallel builds |
| **Isolated Workspaces** | Every task runs in a dedicated git worktree — your main branch stays safe |
| **AI-Powered Merge** | Semantic conflict resolution when integrating worktrees back to main |
| **QA Auto-Fix Loop** | Agents automatically detect, fix, and revalidate failing acceptance criteria |
| **Spec Approval Workflow** | Review and approve AI-generated specifications before implementation begins |
| Platform | Capabilities |
|---|---|
| **GitHub** | Import issues, AI investigation, PR review, batch review wizard, auto-PR creation |
| **GitLab** | Issues and merge request management with AI severity categorization |
| **Azure DevOps** | Work item import, PR review, batch operations — _experimental: backend still returns mock data for several endpoints, see [shared_docs/CONFIGURATION.md](shared_docs/CONFIGURATION.md)_ |
| **Linear** | Bulk issue import with team/project filtering |
| **Jira** | Issue management integration |
| **MCP Marketplace** | Browse, install, and configure Model Context Protocol servers |
| **Custom MCPs** | Define and host custom MCP servers with local authentication |
| **Windsurf** | Windsurf IDE integration via Connect protocol |
高质量的开源AI工作流项目,具有自动化和多智能体编码能力
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,WorkPilot-AI 在Agent工作流赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | WorkPilot-AI |
| Topics | autonomousmulti-agentcodingframework |
| GitHub | https://github.com/tleub-ebp/WorkPilot-AI |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-24 · 更新时间:2026-06-24 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端