Coding agents & developer tools
Code review agents
922 agents · most starred first
Code review agents, page 4 of 10
Multi-agent PR review engine for Claude Code and OpenCode: parallel specialty hunters, an adversarial refuter that challenges every severe finding, and deterministic blocking/advisory tiers. High precision, narrow coverage — lifecycle and state-machine bugs, not style.
A calm, visual view of the true state of your AI-assisted work. Tracks work items from Asked to Verified on evidence, not agent claims, across Claude Code, Codex, git and PRs. Local-first.
Most tools give AI access to the codebase. Archon gives AI access to the change itself. Structural Analysis tool intergrated for AI planning and review workflow both for ai and human ( Claude Code, Codex, OpenCode and Others).
OpenClaw skill: Dynamic bug audit for Node.js web projects (games, data tools, WeChat, APIs, bots). 200+ real-world pitfalls.
Your AI builds the code. Sophia makes sure it's right.
SE-CoVe: Software Engineering Chain-of-Verification plugin for Claude Code
Analyzes code changes via the Gemini API with a structured review prompt, then posts severity-classified findings as GitLab MR notes.
GitHub Action for automated AI code review. Finds bugs, security issues, and suggests improvements. Supports GPT-5.1, Claude, Gemini and local models.
AI platform for GitHub pull requests with a cloud coding agent for autonomous code review, background issue resolution, and automatic PR title/summary generation.
Automated parallel code reviewer using AI Coding Agent CLIs
AI 驱动的多 Pipeline 代码审查 — 安全、逻辑、质量,一个 Action 搞定。
A public, evidence-first agent skill for open-source maintainers: AI-assisted issue triage, PR review, release notes, automation guardrails, and Codex for OSS application prep.
AI pull-request reviewer: hybrid RAG + a code graph + Claude Code/Codex. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Code/Codex plugin.
Local-first diff review for AI-assisted development, you have your own judge.
Turn your team's unwritten code-review conventions into rules your AI coding assistant follows.
🔍 AI-powered code auditor using Rust & Ollama. Features agentic tool-calling architecture where LLM autonomously explores, reads, and analyzes codebases. Detects security vulnerabilities, bugs, and performance issues. Generates detailed Markdown reports with actionable insights.
"Review Ducktective" is an automated code review platform based on an LLM: it takes a diff as input and outputs structured findings with severity levels, linked to specific lines of code, plus RAG navigation through the codebase and a chat with an agent. It also works completely offline (code subject to an NDA must not leave the machine).
baum brings your agents’ code, sessions and decisions into one place, and shows which parts need you
Systematic debugging methodology for AI agents and developers. Prevents common anti-patterns like patch-chaining and wrong-environment restarts.
Open Source Code Review Agent for Context-Aware Large Repositories
Structured protocol for AI coding agents to debate technical decisions via shared markdown
ProPR is an agentic code review system, that can help with unsolicited code reviews as well as join in on pull requests.
Self-hosted AI code review that runs in CI and posts inline comments. 12 AI providers (Claude, GPT-4o, Gemini, Ollama, …), 5 git platforms (GitHub, GitLab, Bitbucket, Azure DevOps, Gitea). BYOK. Rust.
Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, root-cause debugger, and code generator, all in one shell-native loop.
8 AI agents grade your entire repository across 6 dimensions — signed, verifiable A+ to F audit reports in minutes
Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approve, merge, or close.
A fast, read-first code inspector for the agent era: watch AI-written changes land live and review every hunk before it ships
Claude Code skill that audits your product until it stops finding things - then proves it. 24 lenses, 2 convergence loops, 0 hedging.
Claude Code plugin for intelligent GitHub Pull Request reviews that continuously learns your project's conventions and team feedback.
Risk-first agent skill for PR/branch review: blast radius, agent-authored checks, call-graph pincer, structural bar.
PR Guardian AI automatically reviews pull requests using advanced AI analysis. It identifies code issues, security risks, performance problems, and provides actionable suggestions directly inside GitHub pull requests.
AI-powered code guardian — static analysis that watches your entire codebase
Risk-adaptive development pipeline with adversarial consensus code review
AI Code Review Github action, works with any OpenAI compatible service
Embedded code reviews directly directly within pi.
Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI workflow.
Command-Line Agentic Refactoring of Java Code
A PR reviewer bot for AzureDevops using OpenAI/Meta-LLama
LintGPT scans your code for bugs using AI.
Quality gate plugin for Claude Code — blocks insecure, incomplete, and hallucinated AI output. 4 cycles, 28 rules, zero dependencies.
Multi-lens code review MCP server for Claude Code. 8 specialized reviewers run in parallel and return structured verdicts (security, performance, test quality, clean code, and more).
Evidence-backed proof of done for Claude Code, Codex, Cursor, and other AI coding agents. Run real checks, bind results to current Git state, and know what is ready for human review.
AI agent that watches your errors and opens fix PRs
RepoCoder is a Python package that allows you to send your code for review using Large Language Models (LLMs) like Anthropic's Claude or Google's Gemini. It provides an easy way to get code reviews, suggestions for improvements, and more.
Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements
Two-pass code audit skill for Claude Code: adversarial Opus deep review + Codex second opinion
Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.
Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.
Agentic code review with structural graph intelligence — PR gate + branch stewardship. Self-hosted. Apache-2.0.
AI code review MCP server with Zero-Trust approach. Multi-model support, caching, multilingual. Works with Windsurf & Claude Desktop
Ask Codex, Gemini/Antigravity, and Grok (xAI) for second opinions or arbiter-mediated consensus inside Claude Code.
A web app with a suite of AI-driven tools for intelligent code refactoring, style checking, test case generation, and cross-language translation, built with Python, Streamlit, and OpenAI.
Use ChatGPT to conduct code reviews on your pull requests.
Bring free CodeRabbit AI code reviews into Neovim via the CLI
An autonomous, context-aware AI Code Review Agent for GitLab. Powered by multi-LLMs (OpenAI, Anthropic, Gemini) with a self-learning feedback loop to enforce repository best practices.
Claude Code plugin that reviews every edit in plain English so you approve or undo with full context.
Multi-agent AI consultation framework for Claude Code via MCP — get second opinions from OpenAI, Gemini, Qwen, DeepSeek
Dispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks
gradio region:us
Track Al coding assistants by GitHub issues
Kibi is a requirement-conformance layer for AI coding agents that keeps product intent connected to code and tests, and catches when implementations drift from it.
Codex Council adapts the LLM Council method to Codex-only workflows: five independent council roles, compact role outputs, anonymized review, rubric scoring, dissent capture, and chairman synthesis for implementation decisions.
gradio region:us
Adversarial code review for Claude Code. Seven specialist agents review each GitHub PR, GitLab MR or local change for bugs, security, tests and cross-file impact, and an eighth reads the changed code their findings missed. Every finding must survive verification, a skeptical validator and a blind challenge before it posts.
Private, repository-aware AI pull-request reviews in GitHub Actions. BYOK; no Cody-hosted service.
Automated PR reviews powered by a multi-agent AI pipeline — Security, Logic, and Style agents analyze your diffs in parallel and post findings directly to GitHub.
An unattended maintainer for one repository. It reviews, files, prunes, and merges only against proof that a guard bites.
Lint your AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your codebase
Repo-local verification protocol for AI coding agents: acceptance criteria, separate verifier roles, proof artifacts, and evidence-backed done claims.
A command-line tool for developers to get instant code reviews from state-of-the-art Large Language Models (LLMs). Supports both local models (Ollama) and cloud providers (OpenAI, Hugging Face, Azure). Improve code quality, catch bugs, and receive AI-driven feedback effortlessly.
Full-spectrum design patterns skill: Detect anti-patterns, diagnose architectural debt, generate production-ready refactored code. GoF, SOLID, DDD, CQRS, Microservices.
AI-powered PR & issue triage for maintainers. Dedup, scoring, vision doc alignment.
MCP server that wraps the xAI Grok CLI. Lets Claude Code, Cursor, Cline, and any MCP host use Grok as a peer code reviewer, adversary, and second-opinion consultant.
Decision system for software built with AI
Analyze technical debt with cleanliness scores, hotspots, and AI-powered insights.
AI-powered PR reviews running in your Cloud. Your models, your cloud, your rules. No code stored.
Claude Code reviews PRs made by Codex and other AI agents — like CodeRabbit, but agent-to-agent
Automatically reviews code changes in pull requests using OpenAI models to generate thoughtful suggestions for improving code quality.
AI-powered code review CLI tool built with OpenAI Codex SDK. Automatically analyze code for bugs, security issues, and performance problems with structured JSON output.
A 7-agent pre-release audit pipeline for software products. Generic, reusable, AI-native. Inspired by Garry Tan's gstack.
Cross-model audit gate with autonomous quality loop — AST hybrid scanning, fitness gate, blast radius, structured orchestration. 19 MCP tools, 743 tests. CLI + Claude Code plugin.
Install Kodus AI Agents in your own infra.
Comprehensive docstring quality vetting for Python projects
Opus-led Claude Code agent team — strategist plans, Sonnet runners read and fix. Live two-way review-and-fix pipeline. Zero API calls. NOW IN RUST!
Local Claude/Codex PR review loop using existing CLI subscriptions instead of model API keys
Evidence-based review skill for diff, project, and artifact review across code, readiness, architecture, requirements, and risk.
Multi-Agent AI Code Review System - Security, Performance, Logic & Style agents running in parallel via LangGraph + Gemini 1.5 Flash
Local LLM code review CLI for git diffs — review staged/unstaged changes, any git diff range, or a GitHub PR, right in your terminal.
IntelligenceX is a .NET toolkit for the Codex app-server protocol and a GitHub Actions reviewer. It manages the app-server process, speaks JSON-RPC over JSONL, and ships a CLI/web wizard to onboard review automation quickly and safely.
7 Claude Code skills for software architecture review (Python, web, cloud, microservices). Includes A/B benchmarks against unskilled baseline, assertion-graded eval suite, and interactive dashboards.
Stdlib-only Python CLI that orchestrates universal AI agent providers (Claude Code, Codex, Antigravity, OpenRouter, DeepSeek, Groq, local models, Aider) into a multi-agent PR review jury — debate, verify, synthesize one verdict. Local-first, secure by default.
Disciplined minimal code orchestrator with gated multi-model review before subagents ever start writing code.
Practice real coding work in the AI agent era: task challenges and AI PR review drills.
Kit de qualidade de código para o ecossistema Delphi. Reúne modelos, automações de cobertura e diretrizes de Clean Code/TDD para alinhar desenvolvedores e agentes de IA na busca por conformidade estrita com o SonarQube (DelphiSonar)
A live diff monitor for the terminal pane beside your coding agent. Built to stay open, not opened once per review.
Terminal code review with vi-like bindings. Live diffs, comments the agent answers, PR review, MCP built in.
A portable Agent Skill that finds the real constraint limiting an idea, product, codebase, architecture, workflow, or AI agent.
Turn client feedback into pull requests automatically.
An intelligent, AI-powered code review assistant that leverages Retrieval-Augmented Generation (RAG) to provide context-aware, consistent code reviews based on historical review patterns and customizable style guides.
Maker-checker Codex skills for disciplined code changes, independent verification, and safe adaptive parallelism.