CodeRAG

CodeRAG is an AI-powered tool for real-time codebase querying and augmentation using OpenAI and vector search.

Stars: 112

Visit

CodeRAG is an AI-powered code retrieval and assistance tool that combines Retrieval-Augmented Generation (RAG) with AI to provide intelligent coding assistance. It indexes your entire codebase for contextual suggestions based on your complete project, offering real-time indexing, semantic code search, and contextual AI responses. The tool monitors your code directory, generates embeddings for Python files, stores them in a FAISS vector database, matches user queries against the code database, and sends retrieved code context to GPT models for intelligent responses. CodeRAG also features a Streamlit web interface with a chat-like experience for easy usage.

README:

🤖 CodeRAG: AI-Powered Code Retrieval & Assistance

Note: This POC was innovative for its time, but modern tools like Cursor and Windsurf now apply this principle directly in IDEs. This remains an excellent educational project for understanding RAG implementation.

✨ What is CodeRAG?

CodeRAG combines Retrieval-Augmented Generation (RAG) with AI to provide intelligent coding assistance. Instead of limited context windows, it indexes your entire codebase and provides contextual suggestions based on your complete project.

🎯 Core Idea

Most coding assistants work with limited scope, but CodeRAG provides the full context of your project by:

Real-time indexing of your entire codebase using FAISS vector search
Semantic code search powered by OpenAI embeddings
Contextual AI responses that understand your project structure

🚀 Quick Start

Prerequisites

Python 3.11+
OpenAI API Key (Get one here)

Installation

# Clone the repository
git clone https://github.com/your-username/CodeRAG.git
cd CodeRAG

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\\Scripts\\activate

# Install dependencies (installs the package with dev extras)
pip install -r requirements.txt

# Configure environment
cp example.env .env
# Edit .env with your OpenAI API key and settings

The requirements file simply references -e .[dev]; feel free to run pip install -e .[dev] directly if you prefer editable installs.

Configuration

Create a .env file with your settings:

OPENAI_API_KEY=your_openai_api_key_here
OPENAI_EMBEDDING_MODEL=text-embedding-ada-002
OPENAI_CHAT_MODEL=gpt-4
WATCHED_DIR=/path/to/your/code/directory
FAISS_INDEX_FILE=./coderag_index.faiss
EMBEDDING_DIM=1536

Running CodeRAG

# Start the backend (indexing and monitoring)
python main.py

# In a separate terminal, start the web interface
streamlit run app.py

# Query the local index from the terminal (after indexing completes)
coderag-cli "how is faiss configured?"

📖 How It Works

graph LR
    A[Code Files] --> B[File Monitor]
    B --> C[OpenAI Embeddings]
    C --> D[FAISS Vector DB]
    E[User Query] --> F[Semantic Search]
    D --> F
    F --> G[Retrieved Context]
    G --> H[OpenAI GPT]
    H --> I[AI Response]

Indexing: CodeRAG monitors your code directory and generates embeddings for Python files
Storage: Embeddings are stored in a FAISS vector database with metadata
Search: User queries are embedded and matched against the code database
Generation: Retrieved code context is sent to GPT models for intelligent responses

🛠️ Architecture

CodeRAG/
├── 🧠 coderag/           # Core RAG functionality
│   ├── config.py         # Environment configuration
│   ├── embeddings.py     # OpenAI embedding generation
│   ├── index.py          # FAISS vector operations
│   ├── search.py         # Semantic code search
│   └── monitor.py        # File system monitoring
├── 🌐 app.py            # Streamlit web interface
├── 🔧 main.py           # Backend indexing service
├── 🔗 prompt_flow.py    # RAG pipeline orchestration
└── 📋 requirements.txt   # Dependencies

Key Components

🔍 Vector Search: FAISS-powered similarity search for code retrieval
🎯 Smart Embeddings: OpenAI embeddings capture semantic code meaning
📡 Real-time Updates: Watchdog monitors file changes for live indexing
💬 Conversational UI: Streamlit interface with chat-like experience

🎪 Usage Examples

Ask About Your Code

"How does the FAISS indexing work in this codebase?"
"Where is error handling implemented?"
"Show me examples of the embedding generation process"

Get Improvements

"How can I optimize the search performance?"
"What are potential security issues in this code?"
"Suggest better error handling for the monitor module"

Debug Issues

"Why might the search return no results?"
"How do I troubleshoot OpenAI connection issues?"
"What could cause indexing to fail?"

⚙️ Development

Code Quality Tools

# Install pre-commit hooks
pip install pre-commit
pre-commit install
pre-commit run --all-files

Testing

# Test FAISS index functionality
python tests/test_faiss.py

# Test individual components
python scripts/initialize_index.py
python scripts/run_monitor.py

🐛 Troubleshooting

Common Issues

Search returns no results

Check if indexing completed: look for coderag_index.faiss file
Verify OpenAI API key is working
Ensure your query relates to indexed Python files

OpenAI API errors

Verify API key in .env file
Check API usage limits and billing
Ensure model names are correct (gpt-4, text-embedding-ada-002)

File monitoring not working

Check WATCHED_DIR path in .env
Ensure directory contains .py files
Look for error logs in console output

🤝 Contributing

Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Make your changes with proper error handling and type hints
Run code quality checks (pre-commit run --all-files)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

📄 License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

🙏 Acknowledgments

OpenAI for embedding and chat models
Facebook AI Similarity Search (FAISS) for vector search
Streamlit for the web interface
Watchdog for file monitoring

⭐ If this project helps you, please give it a star!

For Tasks:

Click tags to check more tools for each tasks

optimize search performance debug openai connection issues troubleshoot indexing failures implement error handling monitor file changes

For Jobs:

software developer ai engineer data scientist web developer machine learning engineer

Alternative AI tools for CodeRAG

Similar Open Source Tools

CodeRAG

github

: 112

probe

Probe is an AI-friendly, fully local, semantic code search tool designed to power the next generation of AI coding assistants. It combines the speed of ripgrep with the code-aware parsing of tree-sitter to deliver precise results with complete code blocks, making it perfect for large codebases and AI-driven development workflows. Probe is fully local, keeping code on the user's machine without relying on external APIs. It supports multiple languages, offers various search options, and can be used in CLI mode, MCP server mode, AI chat mode, and web interface. The tool is designed to be flexible, fast, and accurate, providing developers and AI models with full context and relevant code blocks for efficient code exploration and understanding.

github

: 110

Shellsage

Shell Sage is an intelligent terminal companion and AI-powered terminal assistant that enhances the terminal experience with features like local and cloud AI support, context-aware error diagnosis, natural language to command translation, and safe command execution workflows. It offers interactive workflows, supports various API providers, and allows for custom model selection. Users can configure the tool for local or API mode, select specific models, and switch between modes easily. Currently in alpha development, Shell Sage has known limitations like limited Windows support and occasional false positives in error detection. The roadmap includes improvements like better context awareness, Windows PowerShell integration, Tmux integration, and CI/CD error pattern database.

github

: 52

TranslateBookWithLLM

TranslateBookWithLLM is a Python application designed for large-scale text translation, such as entire books (.EPUB), subtitle files (.SRT), and plain text. It leverages local LLMs via the Ollama API or Gemini API. The tool offers both a web interface for ease of use and a command-line interface for advanced users. It supports multiple format translations, provides a user-friendly browser-based interface, CLI support for automation, multiple LLM providers including local Ollama models and Google Gemini API, and Docker support for easy deployment.

github

: 113

coding-agent-template

Coding Agent Template is a versatile tool for building AI-powered coding agents that support various coding tasks using Claude Code, OpenAI's Codex CLI, Cursor CLI, and opencode with Vercel Sandbox. It offers features like multi-agent support, Vercel Sandbox for secure code execution, AI Gateway integration, AI-generated branch names, task management, persistent storage, Git integration, and a modern UI built with Next.js and Tailwind CSS. Users can easily deploy their own version of the template to Vercel and set up the tool by cloning the repository, installing dependencies, configuring environment variables, setting up the database, and starting the development server. The tool simplifies the process of creating tasks, monitoring progress, reviewing results, and managing tasks, making it ideal for developers looking to automate coding tasks with AI agents.

github

: 275

qwen-code

Qwen Code is an open-source AI agent optimized for Qwen3-Coder, designed to help users understand large codebases, automate tedious work, and expedite the shipping process. It offers an agentic workflow with rich built-in tools, a terminal-first approach with optional IDE integration, and supports both OpenAI-compatible API and Qwen OAuth authentication methods. Users can interact with Qwen Code in interactive mode, headless mode, IDE integration, and through a TypeScript SDK. The tool can be configured via settings.json, environment variables, and CLI flags, and offers benchmark results for performance evaluation. Qwen Code is part of an ecosystem that includes AionUi and Gemini CLI Desktop for graphical interfaces, and troubleshooting guides are available for issue resolution.

github

: 18.2k

airstore

Airstore is a filesystem for AI agents that adds any source of data into a virtual filesystem, allowing users to connect services like Gmail, GitHub, Linear, and more, and describe data needs in plain English. Results are presented as files that can be read by Claude Code. Features include smart folders for natural language queries, integrations with various services, executable MCP servers, team workspaces, and local mode operation on user infrastructure. Users can sign up, connect integrations, create smart folders, install the CLI, mount the filesystem, and use with Claude Code to perform tasks like summarizing invoices, identifying unpaid invoices, and extracting data into CSV format.

github

: 85

DesktopCommanderMCP

Desktop Commander MCP is a server that allows the Claude desktop app to execute long-running terminal commands on your computer and manage processes through Model Context Protocol (MCP). It is built on top of MCP Filesystem Server to provide additional search and replace file editing capabilities. The tool enables users to execute terminal commands with output streaming, manage processes, perform full filesystem operations, and edit code with surgical text replacements or full file rewrites. It also supports vscode-ripgrep based recursive code or text search in folders.

github

: 4.5k

mcpm.sh

MCPM is an open source CLI tool for managing MCP servers, providing a simplified global configuration approach to install servers once, organize them with profiles, and integrate them into any MCP client. Features include server discovery, direct execution, sharing capabilities, and client integration tools. It eliminates the complexity of v1's target-based system in favor of a clean global workspace model. The tool is designed to be AI agent friendly with comprehensive automation support and a rich CLI interface.

github

: 739

zcf

ZCF (Zero-Config Claude-Code Flow) is a tool that provides zero-configuration, one-click setup for Claude Code with bilingual support, intelligent agent system, and personalized AI assistant. It offers an interactive menu for easy operations and direct commands for quick execution. The tool supports bilingual operation with automatic language switching and customizable AI output styles. ZCF also includes features like BMad Workflow for enterprise-grade workflow system, Spec Workflow for structured feature development, CCR (Claude Code Router) support for proxy routing, and CCometixLine for real-time usage tracking. It provides smart installation, complete configuration management, and core features like professional agents, command system, and smart configuration. ZCF is cross-platform compatible, supports Windows and Termux environments, and includes security features like dangerous operation confirmation mechanism.

github

: 1.8k

zotero-mcp

Zotero MCP seamlessly connects your Zotero research library with AI assistants like ChatGPT and Claude via the Model Context Protocol. It offers AI-powered semantic search, access to library content, PDF annotation extraction, and easy updates. Users can search their library, analyze citations, and get summaries, making it ideal for research tasks. The tool supports multiple embedding models, intelligent search results, and flexible access methods for both local and remote collaboration. With advanced features like semantic search and PDF annotation extraction, Zotero MCP enhances research efficiency and organization.

github

: 513

SMRY

SMRY.ai is a Next.js application that bypasses paywalls and generates AI-powered summaries by fetching content from multiple sources simultaneously. It provides a distraction-free reader with summary builder, cleans articles, offers multi-source fetching, built-in AI summaries in 14 languages, rich debug context, soft paywall access, smart extraction using Diffbot's AI, multi-source parallel fetching, type-safe error handling, dual caching strategy, intelligent source routing, content parsing pipeline, multilingual summaries, and more. The tool aims to make referencing reporting easier, provide original articles alongside summaries, and offer concise summaries in various languages.

github

: 1.2k

codemie-code

Unified AI Coding Assistant CLI for managing multiple AI agents like Claude Code, Google Gemini, OpenCode, and custom AI agents. Supports OpenAI, Azure OpenAI, AWS Bedrock, LiteLLM, Ollama, and Enterprise SSO. Features built-in LangGraph agent with file operations, command execution, and planning tools. Cross-platform support for Windows, Linux, and macOS. Ideal for developers seeking a powerful alternative to GitHub Copilot or Cursor.

github

: 124

VASA-1-hack

VASA-1-hack is a repository containing the VASA implementation separated from EMOPortraits, with all components properly configured for standalone training. It provides detailed setup instructions, prerequisites, project structure, configuration details, running training modes, troubleshooting tips, monitoring training progress, development information, and acknowledgments. The repository aims to facilitate training volumetric avatar models with configurable parameters and logging levels for efficient debugging and testing.

github

: 295

bytebot

Bytebot is an open-source AI desktop agent that provides a virtual employee with its own computer to complete tasks for users. It can use various applications, download and organize files, log into websites, process documents, and perform complex multi-step workflows. By giving AI access to a complete desktop environment, Bytebot unlocks capabilities not possible with browser-only agents or API integrations, enabling complete task autonomy, document processing, and usage of real applications.

github

: 6.6k

MassGen

MassGen is a cutting-edge multi-agent system that leverages the power of collaborative AI to solve complex tasks. It assigns a task to multiple AI agents who work in parallel, observe each other's progress, and refine their approaches to converge on the best solution to deliver a comprehensive and high-quality result. The system operates through an architecture designed for seamless multi-agent collaboration, with key features including cross-model/agent synergy, parallel processing, intelligence sharing, consensus building, and live visualization. Users can install the system, configure API settings, and run MassGen for various tasks such as question answering, creative writing, research, development & coding tasks, and web automation & browser tasks. The roadmap includes plans for advanced agent collaboration, expanded model, tool & agent integration, improved performance & scalability, enhanced developer experience, and a web interface.

github

: 454

For similar tasks

CodeRAG

github

: 112

fast-wiki

FastWiki is an enterprise-level artificial intelligence customer service management system. It is a high-performance knowledge base system designed for large-scale information retrieval and intelligent search. Leveraging Microsoft's Semantic Kernel for deep learning and natural language processing, combined with .NET 8 and React framework, it provides an efficient, user-friendly, and scalable intelligent vector search platform. The system aims to offer an intelligent search solution that can understand and process complex queries, assisting users in quickly and accurately obtaining the needed information.

github

: 387

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 502

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 697

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.3k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.2k