code-reviewer

AI code review with DeepSeek: headless PR review automation that verifies PR descriptions claim-by-claim against real code, checks docs against reality, flags requirement impact, human-in-the-loop + auto review poller + web dashboard

Automated, Pull Request reviews and Issue Triaging powered by Google Gemini. With full codebase context. Installable as a GitHub Action.

Prism Reviewer is an agentic, AI-driven multi-agent code review system orchestrated via LangGraph and LiteLLM. It acts as an autonomous gatekeeper for pull requests by performing targeted static analysis, dependency scanning, AST-based symbol inspection, and parallel LLM-guided code evaluation.

Marketplace of plugins and skills for Claude Code

AI-powered multi-language code reviewer with hybrid scoring, auto-improvement, and user history tracking.

Enterprise-Grade Static Analysis & AI-Powered Refactoring using GitHub Models.

AI-powered developer tool built with LangChain, Google Gemini & Streamlit. Performs 4D automated code audits (bugs, Big-O complexity, OWASP security, refactoring), side-by-side git diffs, conversational Code Copilot, and exportable Markdown/PDF reports.

An AI-powered web app that reviews your code instantly — detects language, estimates complexity & gives smart suggestions. Built with FastAPI + Streamlit.

A brutally honest AI-powered pull request reviewer

A Streamlit application that leverages AutoGen and Ollama to generate and verify code based on user queries. This project provides an interactive interface where users can request specific algorithms or code implementations, and the system automatically generates, reviews, and refines the code to ensure correctness.

An AI-powered programming mentor that reviews code, suggests optimizations, and explains computer science concepts in real-time.

Multi-agent GitHub PR reviewer using LangGraph, FastAPI, and OpenAI/Anthropic/Gemini to deliver consensus-based code, security, and runtime reviews.

AI-powered automatic code review system that analyzes GitHub repositories using multi-agent LLMs. Generates structured insights on security, performance, and maintainability with consensus-based reporting and interactive dashboard visualization.