DevDocs 极客工场-免费私有化技术网页智能中枢（支持VSCode、Claude等20+工具）

DevDocs by CyberAGI 🚀 CyberAGI 🚀 的 DevDocs

Turn Weeks of Documentation Research into Hours of Productive Development
将数周的文档研究转化为数小时的高效开发

Perfect For • Features • Why DevDocs • Getting Started • Scripts • Compare to FireCrawl • Discord
适合 • 特点 • 为什么选择 DevDocs • 开始 • 脚本 • 与 FireCrawl 相比 • 不和

🎯 Perfect For 🎯 适合

🏢 Enterprise Software Developers🏢 企业软件开发人员

Skip weeks of reading documentation and dealing with technical debt. Implement ANY technology faster by letting DevDocs handle the heavy lifting of documentation understanding.
跳过数周阅读文档和处理技术债务的时间。通过让 DevDocs 处理文档理解的繁重工作，更快地实施任何技术。

🕸️ Web Scrapers 🕸️ 网络爬虫

Pull entire contents of websites with Smart Discovery of Child URLs up to level 5. Perfect for both internal and external website documentation with intelligent crawling.
使用子 URL 的智能发现将网站的全部内容提取到第 5 级。非常适合具有智能爬虫功能的内部和外部网站文档。

👥 Development Teams 👥 开发团队

Leverage internal documentation with built-in MCP servers and Claude integration for intelligent data querying. Transform your team’s knowledge base into an actionable resource.
利用内置 MCP 服务器和 Claude 集成的内部文档进行智能数据查询。将团队的知识库转化为可作的资源。

🚀 Indie Hackers 🚀 独立黑客

DevDocs + VSCode(cline) + Your Idea = Ship products fast with ANY technology. No more getting stuck in documentation hell when building your next big thing.
DevDocs + VSCode（cline） + 您的想法 = 使用任何技术快速交付产品。在构建您的下一个大事件时，不再陷入文档地狱。

✨ Features ✨ 特征

🧠 Intelligent Crawling 🧠 智能爬行

• Smart Depth Control: Choose crawl depth from 1-5 levels
  智能深度控制 ：从 1-5 个级别中选择爬行深度
• Automatic Link Discovery: Finds and categorizes all related content
  自动链接发现 ：查找并分类所有相关内容
• Selective Crawling: Pick exactly what you want to extract
  选择性抓取 ：准确选择要提取的内容
• Child URL Detection: Automatically discovers and maps website structure
  子 URL 检测 ：自动发现和映射网站结构

⚡ Performance & Speed ⚡ 性能与速度

• Parallel Processing: Crawl multiple pages simultaneously
  并行处理 ：同时抓取多个页面
• Smart Caching: Never waste time on duplicate content
  智能缓存 ：永远不要在重复内容上浪费时间
• Lazy Loading Support: Handles modern web apps effortlessly
  延迟加载支持 ：轻松处理现代 Web 应用程序
• Rate Limiting: Respectful crawling that won’t overload servers
  速率限制 ：不会使服务器过载的尊重爬网

🎯 Content Processing 🎯 内容处理

• Clean Extraction: Get content without the fluff
  干净提取 ：获取没有绒毛的内容
• Multiple Formats: Export to MD or JSON for LLM fine-tuning
  多种格式 ：导出为 MD 或 JSON 以进行LLM微调
• Structured Output: Logically organized content
  结构化输出 ：逻辑组织的内容
• MCP Server Integration: Ready for AI processing
  MCP 服务器集成 ：为 AI 处理做好准备

🛡️ Enterprise Features 🛡️ 企业功能

• Error Recovery: Auto-retry on failures
  错误恢复 ：失败时自动重试
• Full Logging: Track every operation
  完整日志记录 ：跟踪每个作
• API Access: Integrate with your tools
  API 访问 ：与您的工具集成
• Team Management: Multiple seats and roles
  团队管理 ：多个席位和角色

🤔 Why DevDocs? 🤔 为什么选择 DevDocs？

The Problem 问题

Documentation is everywhere and LLMs are OUTDATED in their knowledge. Reading it, understanding it, and implementing it takes weeks of research and development even for senior engineers. We cut down that time to hours.
文档无处不在，而且LLMs在他们的知识中已经过时了。阅读、理解和实施它需要数周的研发时间，即使对于高级工程师也是如此。 我们将该时间缩短到几个小时。

Our Solution 我们的解决方案

DevDocs brings documentation to you. Point it at any tech documentation URL, and watch as it:
DevDocs 为您提供文档。将其指向任何技术文档 URL，然后观察它：

1. Discovers all related pages to that technology
   发现与该技术相关的所有页面
2. Extracts meaningful content without the fluff
   提取有意义的内容，没有绒毛
3. Organizes information logically inside an MCP server ready for your LLM to query
   在 MCP 服务器中以逻辑方式组织信息，以便您LLM随时查询
4. Presents it in a clean, searchable format in MD or JSON for finetuning LLM purpose
   以 MD 或 JSON 格式以干净、可搜索的格式呈现它，以便进行微调LLM

🔥 We want anyone in the world to have the ability to build amazing products quickly using the most cutting edge LLM technology.
🔥 我们希望世界上的任何人都能够使用最尖端LLM的技术快速构建令人惊叹的产品。

💰 Pricing Comparison 💰 定价比较

🚀 Getting Started 🚀 开始

DevDocs is designed to be easy to use with Docker, requiring minimal setup for new users.
DevDocs 旨在易于与 Docker 一起使用，新用户只需进行最少的设置。

Prerequisites 先决条件

• Docker installed on your system
  您的系统上安装 的 Docker
• Git for cloning the repository
  用于克隆存储库的 Git

Quick Start with Docker (Recommended)Docker 快速入门（推荐）

For Mac/Linux users:对于 Mac/Linux 用户：

# Clone the repository
git clone https://github.com/cyberagiinc/DevDocs.git

# Navigate to the project directory
cd DevDocs

# Start all services using Docker
./docker-start.sh

For Windows users:对于 Windows 用户：

# Clone the repository
git clone https://github.com/cyberagiinc/DevDocs.git

# Navigate to the project directory
cd DevDocs

# Start all services using Docker
docker-start.bat

Note for Windows Users Windows 用户注意事项

If you encounter permission issues, you may need to run the script as administrator or manually set permissions on the logs, storage, and crawl_results directories. The script uses the icacls command to set permissions, which might require elevated privileges on some Windows systems.

Manually Setting Permissions on Windows:

If you need to manually set permissions, you can do so using either the Windows GUI or command line:

Using Windows Explorer:

1. Right-click on each directory (logs, storage, crawl_results)
2. Select "Properties"
3. Go to the "Security" tab
4. Click "Edit" to change permissions
5. Click "Add" to add users/groups
6. Type "Everyone" and click "Check Names"
7. Click "OK"
8. Select "Everyone" in the list
9. Check "Full control" under "Allow"
10. Click "Apply" and "OK"

Using Command Prompt (as Administrator):

icacls logs /grant Everyone:F /T
icacls storage /grant Everyone:F /T
icacls crawl_results /grant Everyone:F /T

Note about docker-compose.yml on Windows
关于 Windows 上的 docker-compose.yml 的注意事项

If you encounter issues with the docker-compose.yml file (such as "Top-level object must be a mapping" error), the docker-start.bat script automatically fixes this by ensuring the file has the correct format and encoding. This fix is applied every time you run the script, so you don’t need to manually modify the file.

This single command will:
这个命令将：

1. Create all necessary directories
   创建所有必要的目录
2. Set appropriate permissions
   设置适当的权限
3. Build and start all Docker containers
   构建并启动所有 Docker 容器
4. Monitor the services to ensure they’re running properly
   监视服务以确保它们正常运行

Accessing DevDocs 访问 DevDocs

Once the services are running:
服务运行后：

• Frontend UI: http://localhost:3001
  前端 UI： http://localhost:3001
• Backend API: http://localhost:24125
  后端 API： http://localhost:24125
• Crawl4AI Service: http://localhost:11235
  Crawl4AI 服务： http://localhost:11235

Logs and Monitoring 日志和监控

When using Docker, logs can be accessed:
使用 Docker 时，可以访问日志：

1. Container Logs (recommended for debugging):
   容器日志 （推荐用于调试）：

   # View logs from a specific container
   docker logs devdocs-frontend
   docker logs devdocs-backend
   docker logs devdocs-mcp
   docker logs devdocs-crawl4ai
   # Follow logs in real-time
   docker logs -f devdocs-backend
   

To stop all services, press Ctrl+C in the terminal where docker-start is running.
要停止所有服务，请在运行 docker-start 的终端中按 Ctrl+C 。

📜 Scripts and Their Purpose📜 脚本及其用途

DevDocs includes various utility scripts to help with development, testing, and maintenance. Here’s a quick reference:
DevDocs 包含各种实用程序脚本，可帮助进行开发、测试和维护。下面是一个快速参考：

Startup Scripts 启动脚本

• start.sh / start.bat / start.ps1 – Start all services (frontend, backend, MCP) for local development.
  start.sh / start.bat / start.ps1 – 启动所有服务（前端、后端、MCP）以进行本地开发。
• docker-start.sh / docker-start.bat – Start all services using Docker containers.
  docker-start.sh / docker-start.bat – 使用 Docker 容器启动所有服务。

MCP Server Scripts MCP 服务器脚本

• check_mcp_health.sh – Verify the MCP server’s health and configuration status.
  check_mcp_health.sh – 验证 MCP 服务器的运行状况和配置状态。
• restart_and_test_mcp.sh – Restart Docker containers with updated MCP configuration and test connectivity.
  restart_and_test_mcp.sh – 使用更新的 MCP 配置重新启动 Docker 容器并测试连接。

Crawl4AI Scripts Crawl4AI 脚本

• check_crawl4ai.sh – Check the status and health of the Crawl4AI service.
  check_crawl4ai.sh – 检查 Crawl4AI 服务的状态和运行状况。
• debug_crawl4ai.sh – Run Crawl4AI in debug mode with verbose logging for troubleshooting.
  debug_crawl4ai.sh – 在调试模式下运行 Crawl4AI，并使用详细日志记录进行故障排除。
• test_crawl4ai.py – Run tests against the Crawl4AI service to verify functionality.
  test_crawl4ai.py – 针对 Crawl4AI 服务运行测试以验证功能。
• test_from_container.sh – Test the Crawl4AI service from within a Docker container.
  test_from_container.sh – 从 Docker 容器中测试 Crawl4AI 服务。

Utility Scripts 实用程序脚本

• view_result.sh – Display crawl results in a formatted view.
  view_result.sh – 在格式化视图中显示爬网结果。
• find_empty_folders.sh – Identify empty directories in the project structure.
  find_empty_folders.sh – 识别项目结构中的空目录。
• analyze_empty_folders.sh – Analyze empty folders and categorize them by risk level.
  analyze_empty_folders.sh – 分析空文件夹并按风险级别对其进行分类。
• verify_reorganization.sh – Verify that code reorganization was successful.
  verify_reorganization.sh – 验证代码重组是否成功。

These scripts are organized in the following directories:
这些脚本组织在以下目录中：

• Root directory: Main scripts for common operations
  根目录：常用作的主脚本
• scripts/general/: General utility scripts
  scripts/general/ ：通用工具脚本
• scripts/docker/: Docker-specific scripts
  scripts/docker/ ：Docker 特定的脚本
• scripts/mcp/: MCP server management scripts
  scripts/mcp/ ：MCP 服务器管理脚本
• scripts/test/: Testing and verification scripts
  scripts/test/ ： 测试和验证脚本

🌍 Built for Developers, by Developers🌍 由开发人员为开发人员构建

DevDocs is more than a tool—it’s your documentation companion that:
DevDocs 不仅仅是一个工具，它是您的文档伴侣：

• Saves Time: Turn weeks of research into hours
  节省时间 ：将数周的研究转化为数小时
• Improves Understanding: Get clean, organized documentation
  提高理解 力：获得干净、有序的文档
• Enables Innovation: Build faster with any technology
  支持创新 ：使用任何技术更快地构建
• Supports Teams: Share knowledge efficiently
  支持团队 ：高效共享知识
• LLM READY: Modern times require modern solutions, using devdocs with LLM is extremely easy and intuitive. With minimal configuration you can run Devdocs and Claude App and recognizes DevDocs’s MCP server ready to chat with your data.
  LLM准备就绪 ：现代需要现代解决方案，使用 devdocs LLM 非常简单直观。只需最少的配置，您就可以运行 Devdocs 和 Claude App，并识别 DevDocs 的 MCP 服务器，随时准备与您的数据聊天。

🛠️ Setting Up the Cline/Roo Cline for Rapid software development.🛠️ 设置 Cline/Roo Cline 以进行快速软件开发。

1. Open the "Modes" Interface
   打开 “Modes” 界面
   • In Roo Code, click the + to create a new Mode-Specific Prompts.
     在 Roo Code 中，点击 + 创建新的 Mode-Specific Prompts。
2. Name 名字
   • Give the mode a Name (e.g., Research_MCP ).
     为模式指定 Name （例如， Research_MCP ）。
3. Role Definition Prompt 角色定义提示
   Prompt 提示

Expertise and Personality: Expertise: Developer documentation retrieval, technical synthesis, and documentation search. Personality: Systematic, detail-oriented, and precise. Provide well-structured answers with clear references to documentation sections.

Behavioral Mandate: Always use the Table Of Contents and Section Access tools when addressing any query regarding the MCP documentation. Maintain clarity, accuracy, and traceability in your responses.

1. Mode-Specific Custom Instructions Prompt
   特定于模式的自定义指令提示
   Prompt 提示

1. Table Of Contents Tool: Returns a full or filtered list of documentation topics. 
2. Section Access Tool: Retrieves the detailed content of specific documentation sections.

General Process: Query Interpretation: Parse the user's query to extract key topics, keywords, and context. Identify the likely relevant sections (e.g., API configurations, error handling) from the query.

Discovery via Table Of Contents: Use the Table Of Contents tool to search the documentation index for relevant sections. Filter or scan titles and metadata for matching keywords.

Drill-Down Using Section Access: For each identified relevant document or section, use the Section Access tool to retrieve its content. If multiple parts are needed, request all related sections to ensure comprehensive coverage.

Synthesis and Response Formation: Combine the retrieved content into a coherent and complete answer. Reference section identifiers or document paths for traceability. Validate that every aspect of the query has been addressed.

Error Handling: If no matching sections are found, adjust the search parameters and retry. Clearly report if the query remains ambiguous or if no relevant documentation is available.

Mandatory Tool Usage: 
Enforcement: Every time a query is received that requires information from the MCP server docs, the agent MUST first query the Table Of Contents tool to list potential relevant topics, then use the Section Access tool to retrieve the necessary detailed content.

Search & Retrieve Workflow: 
Interpret and Isolate: Identify the key terms and data points from the user's query.

Index Lookup: Immediately query the Table Of Contents tool to obtain a list of relevant documentation sections.

Targeted Retrieval: For each promising section, use the Section Access tool to get complete content.

Information Synthesis: Merge the retrieved content, ensuring all necessary details are included and clearly referenced.

Fallback and Clarification: If initial searches yield insufficient data, adjust the query parameters and retrieve additional sections as needed.

Custom Instruction Loading: Additional custom instructions specific to Research_MCP mode may be loaded from the .clinerules-research-mcp file in your workspace. These may include further refinements or constraints based on evolving documentation structures or query types.

Final Output Construction: The final answer should be organized, directly address the query, and include clear pointers (e.g., section names or identifiers) back to the MCP documentation. Ensure minimal redundancy while covering all necessary details.

🤝 Join Our Community 🤝 加入我们的社区

• 🌟 Star us on GitHub
  🌟 在 GitHub 上为我们加注
• 👋🏽 Reach out to our founder on Linkedin
  👋🏽 在 LinkedIn 上联系我们的创始人
• 💬 Join our Discord Community
  💬 加入我们的 Discord 社区

🏆 Success Stories 🏆 成功案例

"DevDocs turned our 3-week implementation timeline into 2 days. It’s not just a crawler, it’s a development accelerator." – Senior Engineer at Fortune 100 Company
“DevDocs 将我们 3 周的实施时间表变成了 2 天。它不仅仅是一个爬网程序，还是一个开发加速器。- 财富 100 强公司高级工程师

"Launched my SaaS in half the time by using DevDocs to understand and implement new technologies quickly." – Successful Indie Hacker
“通过使用 DevDocs 快速了解和实施新技术，将我的 SaaS 启动时间缩短了一半。”

📝 Technology Partners 📝 技术合作伙伴

Star History Star 历史

Made with ❤️ by CyberAGI Inc in 🇺🇸

_{Make Software Development Better Again Contribute to DevDocs}