No API keys required. Transform the native ChatGPT, Claude, and Gemini web interfaces into fully autonomous local coding agents.

MCP server for mandatory peer review between coding assistants like Claude Code, Codex, Gemini, and other CLI agents.

Pi coding agent extension packages — tools, skills, and integrations.

AI-powered PR analyzer with a semantic dependency graph — it knows the blast radius of every code change.

RepoShield: Development of an AI-Powered Automated Code Review Platform with Integrated Application Security Auditing

Adversarial verification layer for AI coding assistants. Based on IACDM — Interactive Adversarial Convergence Development Methodology. The AI proposes. Versus critiques.

An AI-powered code review assistant built using FastAPI, Ollama & Qwen3-8B

Spec-driven multi-agent Codex skill pack with /agent-do commands for planning, execution, reviews, security, design gates, and cross-platform coordination.

A static SAP ABAP code vulnerability scanner

A code review agent with senior-level judgement. It interrogates every changed block against a fixed rubric, runs the real checks, and returns a defensible verdict APPROVE / REQUEST_CHANGES / BLOCK before code is trusted or merged.

AI Code Translator Use AI to translate code from one language to another.

AI-powered code modification assistant that uses Retrieval-Augmented Generation (RAG) to intelligently update code files based on natural language instructions.

AI-powered code review assistant - CodeCraft AI

CodeMind AI is an advanced full-stack platform for automated code reviews, syntax evaluation, and bug detection. Acting as an intelligent virtual pair programmer, it delivers real-time code optimization, logic analysis, and automated vulnerability tracking to streamline workflows.

AI-powered code review on every PR. Flags bugs, security issues, and performance problems automatically using LLaMA 3.3 via Groq.

AI-powered code review for bugs, security vulnerabilities, quality issues, improvement suggestions, and comprehensive testing. Supports manual code input, full GitHub repository analysis, automated edge-case testing, full test suite generation, and CI/CD pipeline simulation.

An open-source ai agent alternative to claude code

AI-powered code review tool — streams PR analysis via MCP server. Built with Next.js, Vercel AI, Claude.

a python linter which evaluates how difficult AI generated code is to read, understand, test, maintain, and safely modify. It gives coding agents actionable and easy to reason about feedback on design problems that traditional linters, type checkers, and tests cannot detect.

A local code-review website with a FastAPI backend, SQLite history, and a React-style HTML/CSS/JavaScript frontend. It reviews pasted code for bugs, vulnerability patterns, risky data loops, and maintainability issues.