AI工作流命令中心
经 AI Skill Hub 精选评估，AI工作流命令中心 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.0 分，适合有一定技术背景的用户使用。
📚 深度解析
AI工作流命令中心 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
AI工作流命令中心 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。
📖 中文文档
AI工作流命令中心 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。
- 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
- 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
# 方式一：npm 全局安装 npm install -g clitrigger # 方式二：npx 直接运行（无需安装） npx clitrigger --help # 方式三：项目依赖安装 npm install clitrigger # 方式四：从源码运行 git clone https://github.com/HyperAITeam/CLITrigger cd CLITrigger npm install npm start
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 命令行使用
clitrigger --help
# 基本用法
clitrigger [options] <input>
# Node.js 代码中使用
const clitrigger = require('clitrigger');
const result = await clitrigger.run(options);
console.log(result);
# clitrigger 配置说明 # 查看配置选项 clitrigger --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 CLITRIGGER_CONFIG="/path/to/config.yml"
简介
<picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/HyperAITeam/CLITrigger/main/src/client/public/logo.svg"> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/HyperAITeam/CLITrigger/main/src/client/public/logo.svg"> <img alt="CLITrigger" src="https://raw.githubusercontent.com/HyperAITeam/CLITrigger/main/src/client/public/logo.svg" width="360"> </picture>
An IDE for AI CLI Agents
Docs, plans, terminals, autonomous agents, and git — one workspace instead of five scattered tools.
<p align="center"> <a href="https://github.com/HyperAITeam/CLITrigger/blob/main/README.md">English</a> · <a href="https://github.com/HyperAITeam/CLITrigger/blob/main/README_KR.md">한국어</a> </p>
<br>
<img src="https://raw.githubusercontent.com/HyperAITeam/CLITrigger/main/docs/images/demo.gif" alt="CLITrigger demo — parallel AI agents executing in isolated worktrees, then morning diff review" width="800">
<br><br>
npm i -g clitrigger && clitriggerOr download the desktop app — no Node.js needed: Windows .exe · macOS .dmg · Linux .AppImage
Up and running in 60 seconds — open http://localhost:3000, set a password, add a project, write TODOs, hit Start.
</div>
---
### Docs → Plan → Terminal → Autonomous Tasks → Version Control. One pipeline. Developing with AI CLI agents (Claude Code, Codex, …) scatters the workflow across disconnected tools: requirements in a note app, plans in another tool, agents across a pile of terminal windows, results in a git client. Editor-centric development has the IDE; CLI-agent-centric development doesn't — so the one ferrying context between tools ends up being you. CLITrigger is that missing IDE. It connects the whole workflow into a single five-stage pipeline — build project knowledge in Docs, shape it into a plan with the planner & calendar, refine it live in terminal sessions, hand it to multiple AI CLIs (Claude Code · Antigravity · Codex) for parallel autonomous execution in isolated git worktrees, and land the results through the review queue and built-in Git client. Each stage inherits the context of the one before it — the intent you captured in docs flows all the way to the merge.
Project knowledge"] --> plan["🗓 Plan
Planner · Calendar"] plan --> term["⌨️ Terminal
Interactive Sessions"] term --> auto["🤖 Autonomous Tasks
Parallel Worktrees"] auto --> vcs["🔀 Version Control
Review Queue · Git"] vcs -. lessons feed back into docs .-> docs
AI CLIs working simultaneously across isolated git worktrees
---
Features
The features follow the five pipeline stages — 📚 Docs → 🗓 Plan → ⌨️ Terminal → 🤖 Autonomous Tasks → 🔀 Version Control — plus the supporting features underneath. Each feature below has a full guide in the Wiki (↗).
📚 1. Docs — build the knowledge
#### Docs (File-based Knowledge) A per-project Obsidian-style knowledge base with a [[wikilink]] graph — inject any file into a prompt, CLI-agnostically. What accumulates here is the input to the whole pipeline. ↗
The Docs tab — browse project markdown with inline preview and a force-directed wikilink graph, then selectively inject files into prompts
Install
npm i -g clitrigger clitrigger
1. Clone & install
git clone https://github.com/HyperAITeam/CLITrigger.git cd CLITrigger npm install cd src/client && npm install && cd ../..
setup screen on first browser load. Set it only if you want to skip setup.
Install cloudflared
winget install cloudflare.cloudflared # Windows brew install cloudflared # macOS
Quick Start
Option A — Desktop App (recommended for end users)
Download the installer for your platform from the latest GitHub release:
- Windows —
CLITrigger-Setup-<version>.exe(NSIS installer) or the portable.exe - macOS —
CLITrigger-<version>.dmg(Apple Silicon & Intel) - Linux —
CLITrigger-<version>.AppImage
The desktop app bundles Node.js and the native modules (better-sqlite3, node-pty, cloudflared), so no separate runtime install is needed. On first launch a setup screen appears in the embedded browser — pick a password there and you're in. External sharing (Cloudflare tunnel) stays paused until setup completes, so the first user is guaranteed to be you.
Option B — npm (recommended for developers)
```bash
Change settings
clitrigger config port 8080 # Change port clitrigger config tunnel on # Enable Cloudflare tunnel for external sharing ```
Prerequisites: Node.js 22+ (use an LTS release), Git, at least one AI CLI (Claude / Antigravity / Codex) Supported Platforms: Windows · macOS · Linux — all core code is cross-platform compatible. Prefer an LTS (even-numbered) Node.js. A brand-new major (e.g. an odd/just-released version) may not have prebuilt native binaries yet, which forces a source build requiring a C++ toolchain (Visual Studio Build Tools on Windows, xcode-select --install on macOS).
2. Configure environment
cp .env.example .env
AUTH_PASSWORD is optional — leave it blank and the dev server will show the
Set TUNNEL_ENABLED=true in .env, then:
npm run start:tunnel
🧰 Supporting the pipeline
#### Analytics Per-project cost and execution stats — by CLI, by status, and over time. ↗
Cost and token usage broken down by CLI, status, and over time
#### Live Logs (Chat & Raw) Real-time WebSocket log streaming in Chat (markdown) or Raw (terminal) mode. ↗
#### Favorites Launcher One-click launcher for your frequent external tools (executables, commands, URLs) from the sidebar. ↗
#### Remote Access Reach CLITrigger from anywhere via Cloudflare Tunnel, with completion notifications and custom-domain routing. ↗
#### MCP Server Expose CLITrigger to any MCP client (Claude Desktop, Claude Code) over an HTTP endpoint — list projects, create and run tasks, and check status just by chatting with your AI. Copy the ready-made config (URL + token) from Settings → MCP; works for npm, desktop, and tunnel users alike. ↗
---
高效的AI工作流管理工具，值得关注
- 构建多智能体协作系统的 Agent 开发者
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- 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
- 构建多智能体协作系统的 Agent 开发者
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
👥 适合人群
🎯 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
- +MIT 协议，可免费商用
- +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
- −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
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。
🔗 相关工具推荐
❓ 常见问题 FAQ
AI Skill Hub 点评：AI工作流命令中心 的核心功能完整，质量优秀。对于自动化工程师和运维人员来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | CLITrigger |
| 原始描述 | 开源AI工作流：A command center for AI coding agents — run Claude, Gemini & Codex in parallel, 。⭐8 · TypeScript |
| Topics | ai-agentsai-automationclaudecodextypescript |
| GitHub | https://github.com/HyperAITeam/CLITrigger |
| License | MIT |
| 语言 | TypeScript |
收录时间：2026-06-17 · 更新时间：2026-06-20 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
🤖 交给 Agent 安装 · AI工作流命令中心
选择 Agent 类型，复制安装指令后粘贴到对应客户端