Coding agents & developer tools

Code review agents

922 agents · most starred first

Code review agents, page 2 of 10

blinky★ 91

An open-source debugging agent in VSCode

redline★ 91

Continuous review for agents

mr-agent★ 91

An open-source multi-agent platform for GitLab MR code review, governance, and CI self-healing.

mr-agent★ 89

mr-agent: A Node.js service that auto-triggers AI-powered code reviews when receiving Git merge request webhook events. Integrates with GitHub/GitLab/Bitbucket to analyze changes, flag issues, and suggest improvements—streamlining reviews for teams of all sizes.

pr-review-agent-council★ 89

学习 learn-claude-code 后的 PR Review Agent 实践项目:构建 Debate Council 多 Agent 审查、Tool Calling、结构化报告与 AI Judge 评估。

beagle★ 88

Agent Skills marketplace: framework-aware skills for code review, documentation, test-plan generation, AI-writing detection, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, and iOS/Swift. Works with Claude Code, Codex, and any agent that supports Agent Skills.

fable-soul★ 87

A judgment layer for AI coding agents - make your AI think, verify, and communicate like a senior engineer

code-buster★ 87

Code Buster reports dependency wiring, dead code, cycles, duplication, complexity, architecture-policy violations, feature flags, security and style heuristics, quality scores, and remediation plans.

MarkuprPlus★ 85

Record your screen, narrate the bug, and hand your AI coding agent structured Markdown - one annotated screenshot per mark. Desktop app, CLI, and MCP server for Claude Code, Cursor, Codex, and Windsurf. On-device Whisper transcription, local-first, MIT.

codebase-audit★ 83

A structured audit playbook for LLM coding agents. One command runs 27 modules across security, dependencies, devops, architecture, performance, compliance, and UX, producing per-module findings, a risk register, and a prioritized remediation plan.

laravel-auditor★ 83

Evidence-based audit methodology and read-only Laravel context tools for existing AI coding agents.

imark★ 82

Native Markdown reader for macOS. Keep it open while you write and it follows every save. Comment on a phrase and the note is saved into the .md file itself. Your coding agent can open a plan here and wait while you mark it up.

chatgpt-code-review-action★ 81

A GitHub Action that uses OpenAI ChatGPT to do code review

ai-agent-agentscope-codereview★ 76

基于 AgentScope Java SDK 的智能代码审查 AI Agent,同时作为 AgentScope 框架学习教程。涵盖 ReAct 模式、工具系统、多 Agent 协作等核心概念。

crg★ 76

Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

nuke-on-rails★ 74

The Rails audit skill for AI coding agents, ranked by blast radius. 🚂☢️

smokinggun★ 73

Help your agents find the smoking gun they're looking for. Optimization evidence for agents: find complexity hotspots.

aegis★ 72

Multi-agent codebase audit for Claude Code — 12 specialized personas with epistemic discourse and bias removal for high-fidelity findings

fossil-mcp★ 71

The code quality toolkit for the agentic AI era. Find dead code, clones, and scaffolding across 15 languages. MCP server + CLI.

tricorder★ 71

Tricorder provides simple, fast, focused feedback when hacking on Haskell (with or without LLM agents).

skills★ 71

Code-quality skills by Max Kanat-Alexander.

boro★ 71

Linux patch review and testing CLI with a multi-stage agentic workflow

ipaship-audit★ 70

Let your AI Agent review your iOS/Android apps for appstore policy & security bugs with ipaShip's web app, cli, mcp or claude-skill with safety hooks layer any any llm agent you use - loopin fixes in dev stage only no more waits till submissions.

lgtm★ 70

Read what your agent wrote before you say LGTM. A fast TUI in Zig for reviewing code with vim motions.

AgentLint★ 68

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

adverse★ 68

Multi-agent adversarial code review for any coding agent

better-code-review-graph★ 67

Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

CodeReviewAgent★ 67

On-demand, context-aware AI code reviews in your Git workflow or IDE as you code.

marg-reviewer★ 66

Code/data for MARG (multi-agent review generation)

coda★ 66

A code companion that lives in Slack

robin-ai-reviewer★ 65

Robin is your AI pull request reviewer in the form of a super fast lightweight github action.

roast-my-design-system★ 65

AI design system scanner + mcp server. Scores repos 0-100, writes fix prompts. 30K+ npm downloads.

DSH-action★ 64

Community GitHub Action for DeepSeek Harness — AI Code Review · CI Diagnosis · Auto Fix · Issue → PR

AICodeBot★ 62

CLI tool that generates commit messages from git changes, reviews code for quality issues, and provides debugging assistance. GitHub Action available for automated PR reviews.

The-Subprime-Code-Crisis★ 62

INDUSTRY ALERT: The Subprime Code Crisis. A data-driven analysis of how AI assistants inflate a bubble of technical debt. Featuring research on 211M lines of code, this report exposes the "Placebo Analytics" of AI productivity and provides a framework for engineering governance.

claude-war-room★ 62

Orquestrador de 5 agentes IA especializados para analise 360 de features com Claude Code. 1 comando, 5 perspectivas, 1 relatorio executivo.

guidedreview★ 62

CLI and a Chrome Extension designed for you to review AI generated code locally and on GitHub PRs

doppelganger★ 60

Similarity detection for Github Issues + AI code reviews

codebase-argus★ 60

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

openrabbit★ 60

Free, AI PR reviewer that runs entirely in GitHub Actions. No hosting required.

VibeDrift★ 59

Ship agentic. Stay coherent. Self-checking code integrity for AI coding agents, via MCP.

dsh-doublecheck★ 59

Double-check before you ship: grill the requirements, test the implementation, prove the delivery. An engineering-discipline bundle for DeepSeek Harness.

rexmod★ 58

Turn Rex into a harness for your coding agent: see what it changed, review it in Neovim, send comments back. Claude Code, Codex, OpenCode, Pi.

knoxchat★ 56

Knox is a vigilant supervisor and management tool that ensures LLM teams rigorously develop reliable AI Agent programming extensions for VSCode and compatible editors.

sofagent★ 56

sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nodes); after departure, audit every change against them. 28 codified audit rules, tamper-evident chain, snapshots, and an MCP toolset (104 tools, 12 plugins). Eve

robin★ 56

Free AI code reviews on every pull request. Bring your own key (OpenRouter free tier works), runs in your repo as a GitHub Action - no quotas, no per-seat fees.

lessloc★ 56

Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works.

snowtree★ 54

Review-Driven Safe AI Coding

matter-ai★ 54

Matter AI is open-source AI Code Reviewer Agent 🤖 for Code Review, Summary Generation, Bug Detection, Security Vulnerabilities and Tests Generation

awesome-ai-code-review★ 54

Awesome list of AI Code Review agents, copilots, and research papers.

multi-agent-review★ 54

Review specs and plans before execution, not code: two model tiers per topic, a reasoning juror only on disagreement, a fail-closed verdict gate

aura★ 53

An audit trail for what AI agents changed in your codebase, and why — signed, per commit, at the symbol level

kiss★ 52

Code-quality feedback for LLM coding agents

Eunomia★ 51

Analyze your code locally using a GPT LLM.

AutoReviewer★ 51

Use LLMs to perform automatic code reviews.

adversarial-review★ 51

Multi-agent code review with Claude + GPT Codex in an adversarial debate loop

eyeball★ 51

Copilot CLI plugin to verify AI document analysis with screenshots from the actual source material

coderabbit-review-helper★ 50

Extract CodeRabbit GitHub PR reviews for AI coding agent consumption

slop-review★ 50

A native /slop-review window for Claude Code, Codex CLI, and pi — review the slop before you ship it. Monaco-powered inline comments, agent reads them back. Forked from badlogic/pi-diff-review.

cli★ 50

Enforce Architecture Decision Records as executable rules — for both humans and AI agents

md-redline★ 50

Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.

sap-engineering-skill★ 50

Atomic SAP ADT CLI and scenario-driven AI skills for ABAP code and business logic analysis, source read/write, Unit/Dump diagnostics, experimental debugging, code review, transport readiness, and SAP integration. Works with Claude Code, Codex, WorkBuddy, OpenCode, and other Agent Skills-compatible tools.

review.nvim★ 50

Review git diffs inside Neovim, comment on specific lines, and export the comments as markdown straight to your AI agent

aristo★ 50

An SDK for verifiable intent, inline with code: one-line claims above your functions, verified at the rigor you choose and flagged when they drift. Agent-first, MIT.

embedded-review★ 50

Embedded/firmware code review skill for AI agents. Memory safety, interrupt correctness, RTOS pitfalls, hardware interfaces, C/C++ traps. STM32/Cortex-M/FreeRTOS focused.

arc42agentic★ 50

Repository zu agentischen Workflows von arc42 Architekturdokumentation, insbesondere Review

dsh-ponytail★ 50

DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill toggles, zero tools, zero-cache-miss | DeepSeek Harness 插件:DietrichGebert/ponytail 懒人 senior 模式与七阶梯子完美移植,6 个技能描述双语自由切换,各个技能自由开关,零 tool 注册,全场景零缓存破坏

pr-cockpit★ 50

An extremely fast GitHub for pull request review: PRs open in 20 ms. Keyboard-first, macOS and Linux, CLI for coding agents.

swift-bylaws★ 50

Architectural linting for Swift developers and coding agents

AgentReady★ 50

Production-readiness static analyzer for Java, Spring Boot, and Spring AI applications.

ProofFlow-v0.1★ 49
baz-cli★ 49

CLI for AI-assisted manual code review

ziglint★ 49

opinionated linting to keep your agent in check

semantic-review★ 49

Semantic diff review for coding agents

duetlens★ 49

Conversational code review on macOS: review a PR or local branch together with a codex agent, and ask about any line instead of just reading its findings.

rexdiff★ 49

Review what your coding agent changed, without leaving Rex. Think herdr-reviewr, but for Rex.

AgentCheck★ 48

Local AI-powered code review agents for Claude Code

Gadfly★ 48

A Socratic supervision layer for AI coding agents.

maintainer-skills-lab★ 48

Curated developer tools, AST analyzers, and automated verification workflows.

deadcode-reaper-skill★ 48

扫出并清除「自称已废」的墓碑 skill、AI 幽灵碎片与死代码,统计释放的 Token 与磁盘。· An agent skill that reaps tombstoned skills, agent leftovers and dead code, reporting tokens reclaimed.

nominal-code★ 47

Automated code reviews posted inline on your pull requests — GitHub and GitLab, any LLM provider, scales from solo dev to org-wide Kubernetes deployment.

llm-code-reviewer★ 47

Automate PR reviews with LLMs like OpenAI GPT and Google Gemini. Supports multilingual reviews, file exclusions, and custom model selection. Simple setup, smarter code reviews!

soplint★ 47

Lint rules for your AI agent's discipline, not its code

sota-scan★ 47

Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do list. A Claude Code skill.

drift★ 47

Review your working changes like a pull request — in the terminal. Block-scoped live diffs, GitHub/GitLab PR review, and send-to-AI-agent.

r3★ 47

Artifacts for any agent harness. Runs locally for a single user. Comment on HTML, docs and diffs, your agent gets the feedback.

ai-review-pipeline★ 46

AI code review pipeline — review, auto-fix, test generation & HTML report in one command. Zero dependencies, 6 AI providers (OpenAI/DeepSeek/Claude/Gemini/Qwen/Ollama), npx ready.

mandu★ 46

An open-source framework that prevents AI agents from breaking your codebase.

code-audit★ 46

Heavy3 Code Audit: Agent skill that uses multi-model consensus to review plans, code, and PRs for coding agents

discuss-cli★ 46

Stop reviewing agent plans in the terminal — PR-style review for Markdown that Codex / Claude Code can reply to.

oh-my-pr★ 46

Autonomous GitHub PR babysitter — watches your repos, triages review feedback, and dispatches AI agents to fix code.

symfony-profiler-optimization-advisor-bundle★ 46

Symfony Profiler meta data collector — reads from Doctrine, Cache, Twig, Events, HTTP Client, Messenger & Stopwatch collectors to detect N+1 queries, slow SQL, cache misses, hot templates & 10 more anti-patterns. Scores findings by impact/effort/confidence/ROI with prepared AI agent prompts. Directly queryable via AI coding tools like Claude Code.

Strictly★ 46

With Strictly, you and your AI agent can see every StrictMode violation. Live.

alint★ 46

🤖🤮 Hate the yuck codes that agents generated? Try `alint`, a ESLint like toolchain for intent driven code check, freeze your skills, AGENTS.md to lint rules

diffo★ 46

Local, live code review for the AI age - read what the agent wrote and send feedback straight back

human-review★ 46

A /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature video, complexity delta, and deep-linked snippets.

claude-review-all★ 45

Comprehensive multi-agent code review for Claude Code

agent-verifier★ 44

🔍 Agent Verifier is a coding agent skill that verifies code against organizational policies, code quality patterns, security requirements, and framework best practices — before code ships. Works with Claude Code, Cursor, Windsurf, and 30+ agents.

review-flow★ 44

Automated AI code reviews powered — webhook-driven, real-time dashboard, MCP integration, smart queue with deduplication, multi-agent audits, and iterative follow-up reviews for GitLab MRs and GitHub PRs

pr-agent★ 44

🚀 A self-hosted AI PR reviewer.

More in Coding agents & developer tools