devrag
🥈SilverDevRag is a lightweight RAG system for Claude Code that enables natural language search of markdown files using multilingual-e5-small embeddings. It helps developers quickly find relevant information without reading entire documents, saving tokens and time. The system connects to local markdown files and integrates with Claude Code for efficient document retrieval.
4370Updated 3mo ago
Intermediate30min to implementautomation
Saves ~120 min per use
Quick InstallView Source
git clone https://github.com/tomohiro-owada/devrag.gitWorks with:
Claude
Overview
About This Skill
DevRag is a free, local RAG system built specifically for developers using Claude Code. It automatically indexes markdown files and enables natural language semantic search, retrieving only relevant document chunks instead of entire files. This approach consumes 40x fewer tokens and executes 15x faster than traditional document reading. The system uses multilingual-e5-small embeddings to support 100+ languages and runs as a single binary with no Python dependencies. DevRag integrates with Claude Code via MCP, auto-discovering documents and allowing developers to find information quickly without knowing exact file names or paths.
How to Use
Download the appropriate binary for your platform from GitHub releases. Add DevRag to your Claude Code configuration via ~/.claude.json with the MCP server command. Create a documents folder and copy your markdown files into it—they auto-index on startup. Search by typing natural language queries like 'JWT authentication methods' directly in Claude Code.
Use Cases
Search technical documentation and API references without reading entire files
Query project notes and design documents with natural language
Find relevant code patterns across multiple markdown guides
Retrieve authentication and security procedures from documentation
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/tomohiro-owada/devragRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
I'm using DevRag to search my [COMPANY] documentation. Please find information about [TOPIC] in the following markdown files: [FILE1.md, FILE2.md, FILE3.md]. Provide a concise summary with key points and relevant code snippets if available.
Example Output
# Summary of [TOPIC] in [COMPANY] Documentation
## Key Points
- [TOPIC] is a critical component in [COMPANY]'s [INDUSTRY] workflows.
- It is primarily used for [PRIMARY PURPOSE] but can also be adapted for [SECONDARY PURPOSE].
- The system integrates with [RELEVANT TOOLS] for enhanced functionality.
## Relevant Code Snippets
```python
# Example code snippet from [FILE1.md]
def example_function():
# Implementation details
pass
```
## Additional Resources
- [FILE2.md] (Lines 45-60): Detailed explanation of [TOPIC] configuration
- [FILE3.md] (Lines 120-135): Troubleshooting common issuesApply to these tools
Browse all toolsClaude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
Drata
Automate security compliance and monitor real-time security posture seamlessly.
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan