能力标签
PilotDeck
⚙️
Agent工作流

PilotDeck

基于 TypeScript · 无代码搭建完整 AI 自动化流程
⭐ 2.7k Stars 🍴 251 Forks 💻 TypeScript 📄 AGPL-3.0 🏷 AI 8.0分
8.0AI 综合评分
AI工作流TypeScript
✦ AI Skill Hub 推荐

PilotDeck 是 AI Skill Hub 本期精选Agent工作流之一。已获得 2.7k 颗 GitHub Star,综合评分 8.0 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。

📚 深度解析

PilotDeck 是一套完整的 AI Agent 自动化工作流方案。随着 AI 能力的不断提升,基于 Agent 的自动化工作流正在成为提升个人和团队效率的核心方式。区别于传统的 RPA 自动化(模拟鼠标键盘操作),AI Agent 工作流通过理解任务意图、动态规划执行路径,能够处理更复杂的非结构化任务。

PilotDeck 工作流的设计遵循"最小配置,最大复用"原则:核心逻辑已经封装好,用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制,在网络波动或 API 限速等情况下仍能稳定运行,适合作为生产环境的自动化基础设施。

在实际部署时,建议先在测试环境中运行 3-5 次,验证各个环节的输出结果符合预期,再部署到生产环境。AI Skill Hub 评分 8.0 分,是同类 Agent 工作流中的精选推荐。

📋 工具概览

PilotDeck 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。

GitHub Stars
⭐ 2.7k
开发语言
TypeScript
支持平台
Windows / macOS / Linux
维护状态
持续维护,定期更新
开源协议
AGPL-3.0
AI 综合评分
8.0 分
工具类型
Agent工作流
Forks
251

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理,如需查看完整原始文档请访问底部「原始来源」。

PilotDeck 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。

📌 核心特色
  • 可视化 Agent 工作流编排,无需编写复杂代码
  • 支持多步骤自动化任务链,实现全流程无人值守
  • 与外部 API、数据库和第三方服务无缝集成
  • 内置错误处理与自动重试机制,保障稳定运行
  • 提供可复用的自动化模板,快速在同类场景部署
🎯 主要使用场景
  • 自动化日常重复性工作,将精力集中于创造性任务
  • 构建数据采集 → 处理 → 输出的完整自动化管线
  • 实现跨平台、跨系统的数据流转和业务协同
以下安装命令基于项目开发语言和类型自动生成,实际以官方 README 为准。
安装命令
# 方式一:npm 全局安装
npm install -g pilotdeck

# 方式二:npx 直接运行(无需安装)
npx pilotdeck --help

# 方式三:项目依赖安装
npm install pilotdeck

# 方式四:从源码运行
git clone https://github.com/OpenBMB/PilotDeck
cd PilotDeck
npm install
npm start
📋 安装步骤说明
  1. 访问 GitHub 仓库获取工作流文件
  2. 在对应平台(Dify / Flowise / Make 等)中找到「导入工作流」功能
  3. 上传工作流文件
  4. 按照提示配置必要的环境变量和 API Key
  5. 运行测试确认流程正常后投入使用
以下用法示例由 AI Skill Hub 整理,涵盖最常见的使用场景。
常用命令 / 代码示例
# 命令行使用
pilotdeck --help

# 基本用法
pilotdeck [options] <input>

# Node.js 代码中使用
const pilotdeck = require('pilotdeck');

const result = await pilotdeck.run(options);
console.log(result);
以下配置示例基于典型使用场景生成,具体参数请参照官方文档调整。
配置示例
# pilotdeck 配置说明
# 查看配置选项
pilotdeck --config-example > config.yml

# 常见配置项
# output_dir: ./output
# log_level: info
# workers: 4

# 环境变量(覆盖配置文件)
export PILOTDECK_CONFIG="/path/to/config.yml"
📑 README 深度解析 真实文档 完整度 69/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理,保留代码块、表格与列表结构。

简介

<p align="center"> <img src="assets/banner.png" alt="PilotDeck" width="680"/> </p>

<p align="center"> Task-oriented AI Agent productivity platform — redefining operational boundaries and memory evolution, one WorkSpace at a time. </p>

<p align="center"> <a href="https://pilotdeck.openbmb.cn"><img src="https://img.shields.io/badge/Website-pilotdeck.openbmb.cn-FF6B35?style=flat-square&logo=googlechrome&logoColor=white" alt="Official Website"/></a> <a href="https://pilotdeck.openbmb.cn/pilotdeck.github.io/demo/p/pilotdeck-demo"><img src="https://img.shields.io/badge/Demo-Live-brightgreen?style=flat-square" alt="Live Demo"/></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-AGPL_3.0-blue.svg?style=flat-square" alt="License"/></a> <a href="https://modelcontextprotocol.io/"><img src="https://img.shields.io/badge/MCP-Native-6366F1?style=flat-square" alt="MCP Native"/></a> <a href="https://github.com/OpenBMB/PilotDeck/stargazers"><img src="https://img.shields.io/github/stars/OpenBMB/PilotDeck?style=flat-square" alt="Stars"/></a> <br/> <a href="#-community"><img src="https://img.shields.io/badge/Discord-Join_Community-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"/></a> &nbsp; <a href="#-community"><img src="https://img.shields.io/badge/Feishu-Community-00D6B9?style=for-the-badge&logo=bytedance&logoColor=white" alt="Feishu"/></a> &nbsp; <a href="https://modelbest.feishu.cn/wiki/UtWxwcERfiRIpIkBOjuc3h9tn1D?fromScene=spaceOverview"><img src="https://img.shields.io/badge/MiniCPM%20Wiki-00D6B9?style=for-the-badge&logo=bytedance&logoColor=white" alt="MiniCPM Wiki"/></a> &nbsp; <a href="#-community"><img src="https://img.shields.io/badge/WeChat-Community-07C160?style=for-the-badge&logo=wechat&logoColor=white" alt="WeChat"/></a> <br/> </p>

<p align="center"> <b>English</b> | <a href="./README.zh.md">简体中文</a> <br/> <a href="https://pilotdeck.openbmb.cn">Website</a> · <a href="https://pilotdeck.openbmb.cn/pilotdeck.github.io/demo/p/pilotdeck-demo">Live Demo</a> · <a href="https://pilotdeck.openbmb.cn/pilotdeck.github.io/docs/en/introduction">Tutorial</a> · <a href="#-installation--quick-start">Quick Start</a> · <a href="#-key-highlights">Highlights</a> · <a href="#use-cases">Use Cases</a> · <a href="#-community">Community</a> </p>

---

News 🔥

  • [2026.05.28] PilotDeck is now open source! Visit our official website at pilotdeck.openbmb.cn. We welcome contributions, feedback, and stars from the community.

---

💡 About PilotDeck

PilotDeck is an open-source agent operating system designed around the concept of "WorkSpace". It is jointly developed and open-sourced by Tsinghua University THUNLP, ModelBest, OpenBMB, and AI9Stars. Targeting general-purpose, multi-task scenarios, PilotDeck is built to be a true productivity tool for the Agent era.

A wave of excellent AI Agent harnesses has emerged in recent years, each with its own focus: Claude Code / Cursor / Trae Solo brought model reasoning deep into the programming IDE; Claude Cowork introduced the notion of project-level isolation to desktop-side knowledge work; WorkBuddy connected agents to IM ecosystems such as WeCom and Feishu so AI is one message away.

When we shift the lens from "one-shot programming" or "immediate Q&A" to long-running, multi-project productivity work, however, several questions remain open:

  • When many projects run in parallel, can memory be white-box and traceable? When the AI gets something wrong, can you pinpoint which memory entry caused it and edit it directly — without starting a new chat from scratch?
  • Can token cost be tracked per task, so that running agents in the background actually becomes economically viable?
  • Can tasks of different difficulty automatically be matched to different models, instead of burning the flagship model on trivial calls?
  • When you step away from the keyboard, can the work keep moving? Can the agent proactively discover what's worth doing, report progress, and land results as files on disk?

PilotDeck is an incremental exploration around exactly these questions. It uses the WorkSpace as the fundamental unit — completely isolating files, memory and skills per project — and pairs it with three pillar capabilities: White-box Memory, Smart Routing and Always-on. The entire system natively supports the Model Context Protocol (MCP) and behaves consistently across front-ends (Web / CLI / IM).

✨ Key Highlights

WorkSpace-Level Isolation & Accretion

Every project gets its own file system, memory store and skill set. Parallel work no longer interferes with itself, retrieval has a bounded scope, and skills accrete naturally as each task grows — no more global context pollution.

<p align="center"> <img src="assets/workspace_en.gif" width="100%" alt="WorkSpace isolation demo"/> </p>

</td> <td width="50%" valign="top">

Traceable White-box Memory

Memory generation, extraction, storage and retrieval are visible end-to-end. When the AI mis-remembers, you can pinpoint and fix the offending entry. Built-in Dream Mode consolidates memory in idle windows, and supports one-click rollback.

<p align="center"> <img src="assets/memory_en.gif" width="100%" alt="White-box memory demo"/> </p>

</td> </tr> <tr> <td width="50%" valign="top">

Smart Routing & Cost Optimization

Task difficulty is auto-detected; complex calls go to flagship models (e.g. Claude 3.5 Sonnet / GPT-4o), simple ones drop to lighter models. Through on-device / cloud co-orchestration and precise matching, token spend shrinks dramatically without sacrificing quality.

<p align="center"> <img src="assets/router.gif" width="100%" alt="Smart routing demo"/> </p>

</td> <td width="50%" valign="top">

Always-on Background Execution

PilotDeck breaks the "you ask, it answers" loop: after you sign off, the agent keeps discovering candidate tasks, running long-horizon monitors, and finally lands deliverables as local files with a summary report waiting for you.

<p align="center"> <img src="assets/awo_en.gif" width="100%" alt="Always-on execution demo"/> </p>

</td> </tr> </table>

📦 Installation & Quick Start

We provide one-line installers for macOS / Linux and Windows PowerShell, plus a source-based workflow for developers.

Option A2: One-line install (Windows PowerShell)

Run PowerShell as a normal user, then execute:

powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/OpenBMB/PilotDeck/main/install.ps1 | iex"

The PowerShell installer uses Windows-native paths under %USERPROFILE%\.pilotdeck, checks Node.js 22.13+ with node:sqlite, installs missing prerequisites with winget when available, builds PilotDeck, and creates a pilotdeck.cmd launcher in %USERPROFILE%\.pilotdeck\bin. Git LFS media assets are optional for the core app; if Git LFS is unavailable or times out, the installer continues without demo videos/GIFs.

After installation, the script starts PilotDeck and prints the UI URL, usually http://localhost:3001. It does not automatically open a browser, so copy that URL into your browser to finish onboarding (provider + API key). You can also open it from PowerShell:

Start-Process http://localhost:3001

If this is your first install, open a new PowerShell window after the script updates your user PATH, then run:

pilotdeck            # starts the server at http://localhost:3001
pilotdeck status     # check runtime status

To open PilotDeck again later, run pilotdeck from a new PowerShell window, then open the printed URL in your browser. If pilotdeck is not yet on PATH, run the launcher directly:

& "$HOME\.pilotdeck\bin\pilotdeck.cmd"

Windows PowerShell FAQ

npm.ps1 cannot be loaded because running scripts is disabled

This can still happen when you run development commands such as npm run dev directly in Windows PowerShell for the first time. PowerShell may resolve npm to npm.ps1, and the default execution policy can block that shim.

Fix it once for the current user, then reopen PowerShell:

Set-ExecutionPolicy -Scope CurrentUser -ExecutionPolicy RemoteSigned

If you do not want to change the user policy, run the cmd shim explicitly instead:

npm.cmd run dev

Native dependency build errors (node-gyp, MSBuild, or Python not found)

The installer normally uses prebuilt packages for native dependencies such as node-pty, better-sqlite3, bcrypt, and sharp. On a fresh Windows machine, if npm cannot download a matching prebuild and falls back to compiling from source, install Visual Studio Build Tools with the C++ workload and Python, then rerun the installer.

GitHub returns 429: Too Many Requests while downloading install.ps1

GitHub may rate-limit repeated raw.githubusercontent.com requests from shared networks. Wait a few minutes and rerun the one-line command, or download install.ps1 from the repository and run it locally with powershell -ExecutionPolicy Bypass -File .\install.ps1.

Option C: Docker Compose

If Docker is installed, you can start PilotDeck with:

docker compose up -d --build

For full Docker configuration, see README_DOCKER.md.

---

Use Cases

All demos below are generated entirely by edge-side models via PilotDeck's Smart Routing — no cloud-side frontier model required.

Work Document Generation

"Survey the Chinese LLM application market and turn it into a formal HTML white paper."
Process Result

Mini-Game Development

"Walk me through building an iOS AR mini-game Ball Finder in Vibe Coding mode."
Process Result

AI Engineering Platform Development

"Build a low-code embedding fine-tuning platform from scratch."
Process Result

Audio-Video Editing & Social Media Operations

"Push this English podcast to a global audience in Chinese / Japanese / French / Korean / Spanish / Arabic."
Process Result (with audio)

https://github.com/user-attachments/assets/a7245467-ee3c-4939-a055-c56576ac56d1

</td> </tr> </table>

---

🖥️ UI & Demo

PilotDeck ships an out-of-the-box Web UI with full WorkSpace management, white-box memory editing, and visualization of multi-agent collaboration.

Option B: From source (for developers)

Need platform-specific dependency installation commands? See the Source Installation Guide.

1. Clone and install dependencies

By default, skip large Git LFS demo media to keep the source install lightweight. If you need the demo videos/GIFs later, run git lfs pull after cloning.
GIT_LFS_SKIP_SMUDGE=1 git clone https://github.com/OpenBMB/PilotDeck.git
cd PilotDeck

node --version          # must be v22.13.0 or newer, and below v23
corepack enable         # enables the pinned pnpm version from package.json
corepack pnpm install --frozen-lockfile --filter pilotdeck --filter pilotdeck-ui

PilotDeck uses the committed pnpm-lock.yaml for reproducible source installs. The filters keep Electron packaging dependencies out of Web-only installs. Prefer the corepack pnpm ... command above instead of npm install; on macOS, this also avoids unnecessary native rebuild fallbacks when matching prebuilt packages are available.

2. Configure a model provider

PilotDeck reads ~/.pilotdeck/pilotdeck.yaml. You can create it manually, or just open the Web UI and configure providers visually in onboarding. Supported protocols include OpenAI, Anthropic, native Google Gemini, DeepSeek, Qwen, Kimi, MiniMax and other OpenAI-compatible endpoints.

If the config file is missing, PilotDeck starts the Web UI without the Gateway and opens onboarding. Saving a valid provider, API key, and model writes the config and starts the Gateway automatically.

schemaVersion: 1
agent:
  model: deepseek/deepseek-v4-pro
model:
  providers:
    deepseek:
      protocol: openai
      url: https://api.deepseek.com/v1
      apiKey: sk-your-api-key

Native Gemini can be configured with protocol: google:

schemaVersion: 1
agent:
  model: google/gemini-3.1-pro-preview
model:
  providers:
    google:
      protocol: google
      url: https://generativelanguage.googleapis.com
      apiKey: ${GEMINI_API_KEY}
      models:
        gemini-3.1-pro-preview: {}

Local Ollama models can be configured without an API key. PilotDeck uses Ollama's OpenAI-compatible /v1/chat/completions endpoint:

ollama serve
ollama pull qwen3:0.6b
schemaVersion: 1
agent:
  model: ollama/qwen3:0.6b
model:
  providers:
    ollama:
      protocol: openai
      url: http://localhost:11434/v1
      models:
        qwen3:0.6b: {}

3. Start the services

```bash cd ui && npm run dev # dev mode (HMR), visit http://localhost:5173

🛠️ Extension Protocol

PilotDeck has an open plugin architecture with a strict boundary between the open-source core and plugin customization. Extending the system is a plugin.json away:

  • MCP Servers — first-class integration with any Model Context Protocol server.
  • Tools & Skills — register custom tools, or pull community skills via ClawHub.
  • Lifecycle Hooks — intercept PreToolUse, UserPromptSubmit, and other critical lifecycle events.
  • Custom Memory — plug in your own memory store provider.

---

🇨🇳 中文文档镜像 AI 翻译 2026-07-06
英文原文章节由系统翻译为中文摘要,便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介

PilotDeck 是一个以“WorkSpace”为核心概念的开源 Agent 操作系统。它由清华大学 THUNLP、ModelBest、OpenBMB 及 AI9Stars 联合开发,旨在应对通用、多任务的复杂场景。通过引入 WorkSpace 设计,PilotDeck 重新定义了 AI Agent 的操作边界与记忆演进方式,为开发者提供了一个高效、可扩展的任务导向型 AI Agent 生产力平台。

⚡ 功能介绍

PilotDeck 实现了 WorkSpace 级别的隔离与增量机制。每个项目都拥有独立的 File System、Memory Store 和 Skill Set,确保并行任务之间互不干扰。这种设计有效避免了全局上下文污染,使检索范围保持在受控边界内,并允许技能随任务的增长自然累积,实现能力的持续进化。

🛠 安装步骤(Docker/pip/源码)

PilotDeck 提供多种安装方式以适应不同用户。推荐 macOS/Linux 用户使用一键安装脚本,该脚本会自动配置 Node.js 22.13+ 环境、克隆仓库并构建前端。对于容器化部署,支持通过 Docker Compose 快速启动。开发者也可以选择从源码构建,以获得更高的定制灵活性。

🚀 使用教程

PilotDeck 支持通过 Smart Routing 技术调用边缘侧模型完成复杂任务,无需依赖云端前沿模型。例如,用户可以要求 Agent “调研中国 LLM 应用市场并将其转化为正式的 HTML 白皮书”,系统将自动完成从信息检索到文档生成的全流程自动化操作。

⚙️ 配置说明(含 MCP / env)

开发者可以通过源码模式进行深度定制。在克隆仓库时,建议安装 Git LFS 以获取大型媒体资产;若仅需核心功能,可通过设置 GIT_LFS_SKIP_SMUDGE=1 来跳过资源下载。系统架构设计清晰,方便开发者根据需求调整开发环境与配置。

🔄 工作流/模块

PilotDeck 采用开放的插件架构,在开源核心与插件定制之间建立了严格的边界。通过 Extension Protocol,用户可以轻松扩展系统功能:支持与任何 MCP (Model Context Protocol) Server 进行一级集成,并允许通过注册自定义 Tools & Skills 来扩展 Agent 的能力边界。

🎯 aiskill88 AI 点评 A 级 2026-06-01

高质量的开源AI工作流平台

📚 实用指南(长尾问题)
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 构建企业知识库 / RAG 检索应用的团队
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
  • 生产部署优先使用 Docker Compose 隔离依赖,并挂载 volume 持久化数据
  • 分块大小建议 256-512 tokens,向量库优选 pgvector 或 Qdrant
  • Agent 任务先做 dry-run 验证工具调用链,再开启自主执行
常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
  • embedding 模型与查询模型不一致导致检索失效
部署方案
  • Docker:PilotDeck 提供官方镜像,docker compose up 一键启动
  • CLI:直接 npm install -g / pip install,命令行调用
  • 云端托管:可放在 Vercel / Railway / Fly.io 等 PaaS 平台

⚡ 核心功能

  • 可视化 Agent 工作流编排,无需编写复杂代码
  • 支持多步骤自动化任务链,实现全流程无人值守
  • 与外部 API、数据库和第三方服务无缝集成
  • 内置错误处理与自动重试机制,保障稳定运行
  • 提供可复用的自动化模板,快速在同类场景部署
👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 构建企业知识库 / RAG 检索应用的团队
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
  • 生产部署优先使用 Docker Compose 隔离依赖,并挂载 volume 持久化数据
  • 分块大小建议 256-512 tokens,向量库优选 pgvector 或 Qdrant
  • Agent 任务先做 dry-run 验证工具调用链,再开启自主执行
⚠️ 常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
  • embedding 模型与查询模型不一致导致检索失效

👥 适合人群

自动化工程师和运维人员项目经理和业务分析师希望减少重复性工作的专业人士数字化转型团队

🎯 使用场景

  • 自动化日常重复性工作,将精力集中于创造性任务
  • 构建数据采集 → 处理 → 输出的完整自动化管线
  • 实现跨平台、跨系统的数据流转和业务协同

⚖️ 优点与不足

✅ 优点
  • +大幅减少重复性人工操作
  • +可视化流程,清晰直观
  • +可扩展性强,支持复杂场景
⚠️ 不足
  • 初始配置和调试需投入一定时间
  • 强依赖外部服务的稳定性
  • 复杂场景需具备一定技术基础
⚠️ 使用须知

该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。

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。

📄 License 说明

⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。

❓ 常见问题 FAQ

PilotDeck 是一款TypeScript开发的AI辅助工具。开源AI工作流:Task-oriented AI Agent productivity platform。⭐2.7k · TypeScript 主要应用场景包括:自动化工作流程。
💡 AI Skill Hub 点评

经综合评估,PilotDeck 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。

⬇️ 获取与下载
⬇ 下载源码(GPL)
⚠️ 本工具使用 AGPL-3.0 协议。您可以自由下载和使用,但衍生作品必须以相同协议开源,不可商业闭源。使用前请确认符合协议要求。
📚 深入学习 PilotDeck
查看分步骤安装教程和完整使用指南,快速上手这款工具
🌐 原始信息
原始名称 PilotDeck
原始描述 开源AI工作流:Task-oriented AI Agent productivity platform。⭐2.7k · TypeScript
Topics AI工作流TypeScript
GitHub https://github.com/OpenBMB/PilotDeck
License AGPL-3.0
语言 TypeScript
🔗 原始来源
🐙 GitHub 仓库  https://github.com/OpenBMB/PilotDeck 🌐 官方网站  https://pilotdeck.openbmb.cn

收录时间:2026-06-01 · 更新时间:2026-06-01 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。