GitHub Pull Request Review Agent

This project implements an AI-powered GitHub pull request review agent. Acting as a Tech Lead-level reviewer, the agent leverages a Retrieval-Augmented Generation (RAG) knowledge base and a Large Language Model (LLM) to provide detailed feedback on pull requests.

Features

• Performance and code optimization analysis.
• Detection of potential bugs and inconsistencies.
• Adherence to coding standards.
• SQL query optimization.
• Comprehensive and diff-based reviews.

Folder Structure

• config/: Contains configuration files for the agent.
• logs/: Stores log files generated during pull request reviews.
• core/: Houses the main functionality and logic of the project.

Getting Started

Refer to the spec.md file for detailed specifications and setup instructions.

Deployment

Deploy Ollama model locally

ollama pull llama3.2:3b-instruct-fp16