DevDocs

DevDocs

Your Documentation Discovery Engine

Stars: 74

Visit
 screenshot

DevDocs is a platform designed to simplify the process of digesting technical documentation for software engineers and developers. It automates the extraction and conversion of web content into markdown format, making it easier for users to access and understand the information. By crawling through child pages of a given URL, DevDocs provides a streamlined approach to gathering relevant data and integrating it into various tools for software development. The tool aims to save time and effort by eliminating the need for manual research and content extraction, ultimately enhancing productivity and efficiency in the development process.

README:

DevDocs 🚀 by CyberAGI Inc

image

Tech documenations suck, we just made it easier for you to digest it inside your LLM.

The idea of DevDocs is to ensure that software engineers and (LLM) software devs dont have to go through copious amount of tech documentation just to implement the tech.

Problem: LLMs are great but they are OUTDATED, as a software developer I had to constantly refer to product knowledge from LlamaIndex, AutoGen and other Machine Learning frameworks to build our Excalibur Platform for cybersecurity and have LLM breakdown the problem. I was copy pasting content from each page into Claude to understand the context and break it down for me and soon the LLM started hallucinating.

Solution: I built a unique platform called DevDocs which spiders through all the child pages of the primary URL, scans if the webpages are live or dead, parses every page (FREE of cost) and converts it into markdown for easy LLM digestion. You can take the markdown and embed into your vector database or use an MCP server like obsidian and load it into Cline for software development.

Goal: I wanted to use state of the art technology but wanted the speed of an up to date LLM, cant do that without an hashtag#MCP(model context protocol) server. So now if I wanted to implement a vector database into my code, I just copy the URL, paste it in DevDocs and the tool grabs all the data from its child websites and spits it into markdown which is then uploaded into my MCP server for Claude to use. This cuts down weeks of research into just a bunch of questions.

Roadmap:

  • [X] Build a Minimum Viable Product with accurate functionality
  • [ ] Handle Complex websites documentation like AWS, MS, langchain :D
  • [X] Adding MCP servers options to choose.
  • [ ] Turnkey Vector Database so all chunking, embedding is done behind the scenes while you sip your joe :)
  • [ ] Agents which will be pros in particular documentation and can code, architect or reason for you with the accurate information as ground truth.
  • [ ] Option to switch to LLM based crawling for specific usecase.
  • [ ] UI Improvements, cuz we flashy.

image

✨ Features

  • 🔍 Smart Discovery: Automatically finds and maps all related documentation pages
  • 📝 Markdown Conversion: Converts web content into clean, readable markdown
  • 🌐 Deep Crawling: Intelligently navigates through complex documentation structures
  • 🎯 Precision Extraction: Focuses on meaningful content while filtering out noise
  • 🚄 Real-time Progress: Live updates on crawling progress and statistics
  • 💫 Modern UI: Sleek, responsive interface with real-time feedback
  • 🔥 Inbuilt MCP Server: No need to copy paste into your MCP server, DevDocs already has an inbuild MCP server, already connect to your claude desktop app upon installation(restart needed) and gives you the commands you need to add to your cline MCP server configs. How cool is that?

🚀 Getting Started

# 1. Clone and install everything
git clone https://github.com/cyberagiinc/DevDocs.git && cd DevDocs && ./fast-markdown-mcp/setup.sh

# 2. Start all services
./start.sh

That's it! The system will:

  • Install all dependencies (npm, Python backend, MCP server)
  • Configure Claude Desktop integration
  • Start all services automatically
  • Open the application in your browser (http://localhost:3001)

💡 How to Use DevDocs: Super Difficult :)

  1. Enter a documentation URL (e.g., https://docs.crawl4ai.com)
  2. Click "Discover" to find all related pages
  3. Review the discovered pages in the list
  4. Click "Crawl All Pages" to extract content. Go get some coffee, because it takes a while.
  5. Download the generated markdown/json or use it with an inbuilt MCP server with Cline/Claude

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Commit your changes
  4. Push to the branch
  5. Open a Pull Request

📄 License

Apache-2.0 license

Star History

Star History Chart

Built with ❤️ by CyberAGI Inc. & Shubham Khichi

For Tasks:

Click tags to check more tools for each tasks

For Jobs:

Alternative AI tools for DevDocs

Similar Open Source Tools

For similar tasks

For similar jobs