Integrates with Claude to enable intelligent querying of documentation data, transforming crawled technical documentation into an actionable resource that LLMs can directly interact with.
Turn Weeks of Documentation Research into Hours of Productive Development
Perfect For • Features • Why DevDocs • Getting Started • Scripts • Compare to FireCrawl • Discord
Skip weeks of reading documentation and dealing with technical debt. Implement ANY technology faster by letting DevDocs handle the heavy lifting of documentation understanding.
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.
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.
DevDocs + VSCode(cline) + Your Idea = Ship products fast with ANY technology. No more getting stuck in documentation hell when building your next big thing.
Documentation is everywhere and LLMs are OUTDATED in their knowledge.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.
DevDocs brings documentation to you. Point it at any tech documentation URL, and watch as it: 1. Discovers all related pages to that technology 2. Extracts meaningful content without the fluff 3. Organizes information logically inside an MCP server ready for your LLM to query 4. Presents it in a clean, searchable format in MD or JSON for finetuning LLM purpose
? We want anyone in the world to have the ability to build amazing products quickly using the most cutting edge LLM technology.
| Feature | DevDocs | Firecrawl |
|---|---|---|
| Free Tier | Unlimited pages | None |
| Starting Price | Free Forever | $16/month |
| Enterprise Plan | Custom | $333/month |
| Crawl Speed | 1000/min | 20/min |
| Depth Levels | Up to 5 | Limited |
| Team Seats | Unlimited | 1-5 seats |
| Export Formats | MD, JSON, LLM-ready MCP servers | Limited formats |
| API Access | Coming Soon | Limited |
| Model Context Protocol Integration | ✅ | ❌ |
| Support | Priority Available via Discord | Standard only |
| Self-hosted (free use) | ✅ | ❌ |
DevDocs is designed to be easy to use with Docker, requiring minimal setup for new users.
For Mac/Linux users:
# Clone the repository
git clone https://github.com/cyberagiinc/DevDocs.git
# Navigate to the project directory
cd DevDocs
# Configure environment variables
# Copy the template file to .env
cp .env.template .env
# Ensure NEXT_PUBLIC_BACKEND_URL in .env is set correctly (e.g., http://localhost:24125)
# This allows the frontend (running in your browser) to communicate with the backend service.
# Start all services using Docker
./docker-start.shFor Windows users: Experimental Only (Not Tested Yet)
# Clone the repository
git clone https://github.com/cyberagiinc/DevDocs.git
# Navigate to the project directory
cd DevDocs
# Configure environment variables
# Copy the template file to .env
copy .env.template .env
# Ensure NEXT_PUBLIC_BACKEND_URL in .env is set correctly (e.g., http://localhost:24125)
# This allows the frontend (running in your browser) to communicate with the backend service.
# Prerequisites: Install WSL 2 and Docker Desktop
# Docker Desktop for Windows requires WSL 2. Please ensure you have WSL 2 installed and running first.
# 1. Install WSL 2: Follow the official Microsoft guide: https://learn.microsoft.com/en-us/windows/wsl/install
# 2. Install Docker Desktop for Windows: Download and install from the official Docker website. Docker Desktop includes Docker Compose.
# Start all services using Docker
docker-start.baticacls logs /grant Everyone:F /T
icacls storage /grant Everyone:F /T
icacls crawl_results /grant Everyone:F /TThis single command will: 1. Create all necessary directories 2. Set appropriate permissions 3. Build and start all Docker containers 4. Monitor the services to ensure they're running properly
Once the services are running: - Frontend UI: http://localhost:3001 - Backend API: http://localhost:24125 - Crawl4AI Service: http://localhost:11235
When using Docker, logs can be accessed :
# 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-backendTo stop all services, press Ctrl+C in the terminal where docker-start is running.
DevDocs includes various utility scripts to help with development, testing, and maintenance. Here's a quick reference:
start.sh / start.bat / start.ps1 - Start all services (frontend, backend, MCP) for local development.docker-start.sh / docker-start.bat - Start all services using Docker containers.check_mcp_health.sh - Verify the MCP server's health and configuration status.restart_and_test_mcp.sh - Restart Docker containers with updated MCP configuration and test connectivity.check_crawl4ai.sh - Check the status and health of the Crawl4AI service.debug_crawl4ai.sh - Run Crawl4AI in debug mode with verbose logging for troubleshooting.test_crawl4ai.py - Run tests against the Crawl4AI service to verify functionality.test_from_container.sh - Test the Crawl4AI service from within a Docker container.view_result.sh - Display crawl results in a formatted view.find_empty_folders.sh - Identify empty directories in the project structure.analyze_empty_folders.sh - Analyze empty folders and categorize them by risk level.verify_reorganization.sh - Verify that code reorganization was successful.These scripts are organized in the following directories:
- Root directory: Main scripts for common operations
- scripts/general/: General utility scripts
- scripts/docker/: Docker-specific scripts
- scripts/mcp/: MCP server management scripts
- scripts/test/: Testing and verification scripts
DevDocs is more than a tool—it's your documentation companion that: - Saves Time: Turn weeks of research into hours - Improves Understanding: Get clean, organized documentation - Enables Innovation: Build faster with any technology - Supports Teams: Share knowledge efficiently - 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.
In Roo Code, click the + to create a new Mode-Specific Prompts.
Name
Research_MCP).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. 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."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
"Launched my SaaS in half the time by using DevDocs to understand and implement new technologies quickly." - Successful Indie Hacker
Made with ❤️ by CyberAGI Inc in ??
Make Software Development Better Again Contribute to DevDocs