能力标签

🤖 Agent 🔄 工作流 💻 CLI 🧠 Claude ✨ GPT ⌨️ Cursor

⚙️

Agent工作流

AI工作流

基于 Python · 无代码搭建完整 AI 自动化流程

英文名：aidlc-workflows

⭐ 3.4k Stars 🍴 550 Forks 💻 Python 📄 MIT-0 🏷 AI 8.2分

8.2AI 综合评分

AI工作流Python

⚙️ 配置说明 📺 TG 频道

✦ AI Skill Hub 推荐

AI Skill Hub 强烈推荐：AI工作流是一款优质的Agent工作流。已获得 3.4k 颗 GitHub Star，AI 综合评分 8.2 分，在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案，这是一个值得深入了解的选择。

📚 深度解析

AI工作流是一套完整的 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。

AI工作流工作流的设计遵循"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 8.2 分，是同类 Agent 工作流中的精选推荐。

📋 工具概览

AI工作流是一套完整的 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

⭐ 3.4k

开发语言

Python

支持平台

Windows / macOS / Linux

维护状态

持续维护，定期更新

开源协议

MIT-0

AI 综合评分

8.2 分

工具类型

Agent工作流

Forks

550

📖 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」。

📌 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：pip 安装（推荐）
pip install aidlc-workflows

# 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 aidlc-workflows

# 方式三：从源码安装（获取最新功能）
git clone https://github.com/awslabs/aidlc-workflows
cd aidlc-workflows
pip install -e .

# 验证安装
python -c "import aidlc_workflows; print('安装成功')"

📋 安装步骤说明

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

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
aidlc-workflows --help

# 基本用法
aidlc-workflows input_file -o output_file

# Python 代码中调用
import aidlc_workflows

# 示例
result = aidlc_workflows.process("input")
print(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

# aidlc-workflows 配置文件示例（config.yml）
app:
  name: "aidlc-workflows"
  debug: false
  log_level: "INFO"

# 运行时指定配置文件
aidlc-workflows --config config.yml

# 或通过环境变量配置
export AIDLC_WORKFLOWS_API_KEY="your-key"
export AIDLC_WORKFLOWS_OUTPUT_DIR="./output"

📑 README 深度解析真实文档完整度 90/100 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。

AI-DLC (AI-Driven Development Life Cycle)

Key Features

Feature	Description
Adaptive Intelligence	Only executes stages that add value to your specific request
Context-Aware	Analyzes existing codebase and complexity requirements
Risk-Based	Complex changes get comprehensive treatment, simple changes stay efficient
Question-Driven	Structured multiple-choice questions in files, not chat
Always in Control	Review execution plans and approve each phase
Extensible	Layer custom rules e.g. security, compliance, and organization-specific rules on top of the core workflow

---

Prerequisites

Have one of our supported platforms/tools for Assisted AI Coding installed:

Platform	Installation Link
Kiro	[Install](https://kiro.dev/)
Kiro CLI	[Install](https://kiro.dev/cli/)
Amazon Q Developer IDE Plugin	[Install](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/q-in-IDE.html)
Cursor IDE	[Install](https://cursor.com/)
Cline VS Code Extension	[Install](https://marketplace.visualstudio.com/items?itemName=saoudrizwan.claude-dev)
Claude Code CLI	[Install](https://github.com/anthropics/claude-code)
GitHub Copilot	[Install](https://marketplace.visualstudio.com/items?itemName=GitHub.copilot) + [Chat](https://marketplace.visualstudio.com/items?itemName=GitHub.copilot-chat)

---

---

Experimental: AI-Assisted Setup (Release Download)

Instead of manually copying files, let your AI agent handle the setup. This is an experimental workflow — currently validated with Kiro, Claude code, Cursor, Antigravity. Note: This approach requires your agent to have shell access (e.g., Kiro, Claude Code, Cline). For agents without shell access, follow the Common setup above.

Paste this prompt into your AI agent:

Set up AI-DLC in this project by doing the following:

1. Download the latest AI-DLC release:
   - Use the GitHub API to find the latest release asset URL:
     curl -sL https://api.github.com/repos/awslabs/aidlc-workflows/releases/latest \
       | grep -o '"browser_download_url": *"[^"]*"' \
       | head -1 \
       | cut -d'"' -f4
   - Download the zip from that URL to /tmp/aidlc-rules.zip
   - Extract it: unzip -o /tmp/aidlc-rules.zip -d /tmp/aidlc-release
   - Copy the aidlc-rules/ folder from the extracted contents into .aidlc at the project root
   - Clean up: rm -rf /tmp/aidlc-rules.zip /tmp/aidlc-release

2. Create the appropriate rules/steering file for your IDE using the options below.
   Pick the one that matches the agent you are running in:

   - Kiro IDE or Kiro CLI     → create `.kiro/steering/ai-dlc.md`
   - Amazon Q Developer       → create `.amazonq/rules/ai-dlc.md`
   - Antigravity              → create `.agent/rules/ai-dlc.md`
   - Cursor                   → create `.cursor/rules/ai-dlc.mdc` with frontmatter:
                                  ---
                                  description: "AI-DLC workflow"
                                  alwaysApply: true
                                  ---
   - Cline                    → create `.clinerules/ai-dlc.md`
   - Claude Code              → create `CLAUDE.md`
   - GitHub Copilot           → create `.github/copilot-instructions.md`
   - Any other agent          → create `AGENTS.md`

3. The file content should be:
   When the user invokes AI-DLC, read and follow
   `.aidlc/aidlc-rules/aws-aidlc-rules/core-workflow.md` to start the workflow.

4. Add `.aidlc` to `.gitignore` unless I explicitly ask you not to.

5. Confirm what file you created and that `.aidlc` is gitignored.

The agent will download the latest release, create the correct config file for your IDE, and gitignore the .aidlc directory automatically.

Updating AI-DLC — Re-run the prompt above. The agent will download the latest release and overwrite the existing .aidlc/ folder.

---

Usage

Start any software development project by stating your intent starting with the phrase "Using AI-DLC, ..." in the chat
AI-DLC workflow automatically activates and guides you from there
Answer structured questions that AI-DLC asks you
Carefully review every plan that AI generates. Provide your oversight and validation
Review the execution plan to see which stages will run
Carefully review the artifacts and approve each stage to maintain control
All the artifacts will be generated in the aidlc-docs/ directory

---

Local-only settings

.claude/settings.local.json ```

---

Generated aidlc-docs/ Reference

For the complete reference of all documentation artifacts generated by the AI-DLC workflow, see docs/GENERATED_DOCS_REFERENCE.md.

---

Amazon Q Developer IDE Plugin/Extension

AI-DLC uses Amazon Q Rules within your project workspace.

The commands below assume you extracted the zip to your Downloads folder so that the resulting path is Downloads/aidlc-rules/. If you used a different location, replace Downloads with your actual folder path.

[!NOTE] Windows users: if you used File Explorer's Extract All... dialog, it defaults to creating a wrapper folder named after the zip (e.g., ai-dlc-rules-v0.1.8\aidlc-rules\...). Either uncheck/edit that destination so the contents land directly in Downloads\aidlc-rules\ (matching the commands below), or prepend ai-dlc-rules-v<version>\ to each Downloads\ path in the commands — substituting <version> with the release you downloaded.

On macOS/Linux:

mkdir -p .amazonq/rules
cp -R ~/Downloads/aidlc-rules/aws-aidlc-rules .amazonq/rules/
cp -R ~/Downloads/aidlc-rules/aws-aidlc-rule-details .amazonq/

On Windows (PowerShell):

New-Item -ItemType Directory -Force -Path ".amazonq\rules"
Copy-Item -Recurse "$env:USERPROFILE\Downloads\aidlc-rules\aws-aidlc-rules" ".amazonq\rules\"
Copy-Item -Recurse "$env:USERPROFILE\Downloads\aidlc-rules\aws-aidlc-rule-details" ".amazonq\"

On Windows (CMD):

mkdir .amazonq\rules
xcopy %USERPROFILE%\Downloads\aidlc-rules\aws-aidlc-rules .amazonq\rules\aws-aidlc-rules\ /E /I
xcopy %USERPROFILE%\Downloads\aidlc-rules\aws-aidlc-rule-details .amazonq\aws-aidlc-rule-details\ /E /I

Your project should look like:

<project-root>/
    ├── .amazonq/
    │     ├── rules/
    │     │     ├── aws-aidlc-rules/
    │     ├── aws-aidlc-rule-details/

To verify the rules are loaded:

In the Amazon Q Chat window, click the Rules button in the lower right corner.
Confirm you see entries for .amazonq/rules/aws-aidlc-rules.

---

cat > .cursor/rules/ai-dlc-workflow.mdc << 'EOF'

description: "AI-DLC (AI-Driven Development Life Cycle) adaptive workflow for software development"

Three-Phase Adaptive Workflow

AI-DLC follows a structured three-phase approach that adapts to your project's complexity:

Extensions

AI-DLC supports an extension system that lets you layer additional rules on top of the core workflow. Extensions are markdown files organized under aws-aidlc-rule-details/extensions/ and grouped by category (e.g., security/, testing/, resiliency/).

How Extensions Work

Each extension consists of two files placed in the same directory:

A rules file (e.g., security-baseline.md) containing the extension's rules.
An opt-in file (e.g., security-baseline.opt-in.md) containing a structured multiple-choice question presented to the user during Requirements Analysis.

At workflow start, AI-DLC scans the extensions/ directory and loads only *.opt-in.md files. During Requirements Analysis, it presents each opt-in prompt to the user. When the user opts in, the corresponding rules file is loaded (derived by naming convention: strip .opt-in.md, append .md). When the user opts out, the rules file is never loaded. Extensions without a matching *.opt-in.md file are always enforced.

Once enabled, extension rules are blocking constraints — at each stage, the model verifies compliance before allowing the stage to proceed.

Built-in Extensions

The extensions/ directory ships with the following (new extensions may be added over time):

aws-aidlc-rule-details/
└── extensions/
    ├── security/                      # Extension category
    │   └── baseline/
    │       ├── security-baseline.md          # Baseline security rules
    │       └── security-baseline.opt-in.md   # Opt-in prompt
    ├── testing/                       # Extension category
    │   └── property-based/
    │       ├── property-based-testing.md          # Property-based testing rules
    │       └── property-based-testing.opt-in.md   # Opt-in prompt
    ├── resiliency/
    │   └── baseline/
    │       ├── resiliency-baseline.md          # Baseline resiliency rules
    │       └── resiliency-baseline.opt-in.md   # Opt-in prompt

[!IMPORTANT] The security extension rules are provided as a directional reference for building effective security rules within AI-DLC workflows. Each organization should build, customize, and thoroughly test their own security rules before deploying in production workflows. The resiliency extension rules are provided as a directional best practices for building resilient workloads rules within AI-DLC workflows. Each organization should build, customize, and thoroughly test their own resiliency rules before deploying in production workflows.

Adding Your Own Extensions

You can extend an existing category or create an entirely new one.

1. Create a directory under extensions/ (e.g., security/compliance/ or performance/baseline/). 2. Add a rules file (e.g., compliance.md). Follow the same structure as security-baseline.md: - Define each rule as a heading in the format ## Rule <PREFIX-NN>: <Title> where the prefix is a short category identifier and NN is a sequential number (e.g., COMPLIANCE-01, COMPLIANCE-02). These IDs are referenced in audit logs and compliance summaries, so they must be unique across all loaded extensions. - Include a Rule section describing the requirement. - Include a Verification section with concrete checks the model should evaluate. 3. Add a matching opt-in file using the naming convention <name>.opt-in.md (e.g., compliance.opt-in.md). See security-baseline.opt-in.md for the expected format. Omitting this file means the extension is always enforced with no user opt-out. 4. Rules are blocking by default — if verification criteria are not met, the stage cannot proceed until the finding is resolved.