Coding agents & developer tools
Code review agents
922 agents · most starred first
Code review agents, page 7 of 10
🧪 A Claude Code, OpenCode & Codex plugin that blocks git push until you pass a quiz on the AI-written diff you're shipping — code review you can't rubber-stamp.
Harness engineering for AI coding agents. Guides steer the agent before it acts, sensors catch what it got wrong after: a project constitution and concern catalogs, 12 read-only review agents, a 12-gate commit chain, and loop closure that blocks commits lacking closure evidence.
K-LLM orchestrated code review for OpenCode. Dispatches 6 parallel review passes across different AI models, synthesizes findings with majority voting, and validates to eliminate false positives.
One writes, one reviews — worker 与 reviewer 上下文隔离的 AI 编码工作流 Harness,以项目验证命令、风险门禁和运行证据判断任务能否完成。
TUI tool for quick local reviews
Native macOS desktop client for reviewing GitHub pull requests — PR dashboard, AI review drafts, CI diagnostics, and merge controls in one window.
AI agent that reviews GitHub pull requests via multi-step tool calling
Structural context for AI code reviews. Resolves blast radius through the TypeScript type system.
The multi-agent coding loop that covers every angle — one model builds, independent AI models review it from every direction, tests decide, you hold the final gate. Privacy-enforced, anti-drift, self-improving.
Automatic isolated secondary review for Pi coding agent sessions
Resident peer agents for pi — long-running partners inside your session that tick on their own rhythm, watch the work, and push findings back into the conversation.
Deep bug audit for coding agents: three sweeps, 12 named defect classes, findings marked confirmed vs hypothesis, a mandatory coverage table, defined P0/P1/P2 — then autonomous fixing, questions only at the end. Works in Claude Code, Cursor, Windsurf, Copilot, Codex and anything reading AGENTS.md
专为AI Agent设计的轻量级思维树+代码深度分析插件。两级触发链(开启思维树→开启深度思考模式),耦合基因库省Token,支持5语言函数级分析、安全/性能/逻辑检测、沙箱动态测试。零依赖,手机端Termux流畅运行。
证据约束的代码诊断工作台:确定性静态分析拥有源码事实,LLM 只提假设,resolver/validator 决定能否绑定回真实操作——证据不足保持 unknown/abstained,从架构抑制幻觉。已在真实开源项目发现 bug(stunner #89 已被上游确认修复)。Python。
Universal multi-agent quality gate for Claude Code, Codex, Cursor and Gemini CLI — research, test, Red Team, verify and judge AI-generated work before release.
Multi-agent quality gate skill for Claude Code that researches, reviews, tests and challenges AI-generated work before the final answer.
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.
Nitpicker — a hostile audit toolkit for coding agents. One skill, one entry point, a full deck of audit command: Assumes the code is incorrect until proven otherwise. Every command files findings with evidence and a concrete fix — no compliments, no hedging.
Four Claude Code review agents that check your work before it ships: code-reviewer (quality), ai-signal-reviewer (AI writing tells in prose), deploy-guard (stack-aware release-readiness), and pr-validator (runs a PR's tests and gives a release verdict). Each runs in its own context and reports without editing your files.
Let Claude Code and Codex review each other's code from your current session. One-line install for macOS / Linux / WSL2 sets up the official CLIs if missing; uses your existing Claude / ChatGPT subscription.
Production-ready AI Code Review Agent built with Google Cloud Agent Development Kit (ADK). Reviews pull requests via GitHub webhooks and posts structured feedback as PR comments.
AI agent that watches GitHub PRs for changes that silently contradict documented architectural decisions (ADRs) — and alerts the responsible engineer via Telegram before the code merges. Two-stage RAG pipeline with section-level ADR chunking, rejected-alternative detection, and corpus gap signals for self-healing knowledge bases.
Autonomous AI agent that reviews GitHub PRs for bugs, security vulnerabilities & code quality issues — powered by LangGraph, Llama 3.3 70B, and Langfuse observability. Includes evaluation benchmarks with honest metrics.
Automate code reviews with AI Code Review Assistant.
Multi-agent framework for AI-assisted development. Guides, reviews, and validates — instead of writing code for you.
PM + Dev + QA agents engineered for structure, security, and short context windows.
Multi-agent code review CLI using NVIDIA Nemotron 3 Super
Multi agent automatically reviews Python code for security vulnerabilities, performance bottlenecks, stylistic errors, and semantic issues.
An ai agent that critically reviews PRs
Multi-agent AI code review system that uses consensus between specialized agents to provide high-quality inline feedback.
A powerful AI-powered tool to analyze, optimize, and transform your code into high-performance, quality software.
Ralphex is a Claude Code plugin that uses Claude Code as planner + implementer, and Codex as code reviewer
A Claude Code skill that dispatches 7 specialized parallel reviewers for comprehensive production-readiness code review
A CLI for generating LLM-backed metrics for deciding how closely to review code
An AI-powered multi-agent system for automated code reviews. Uses specialized LLM agents to analyze security, performance, style, and best practices.
Read-only AI code reviewer. Diff in, structured findings out. No write tools, no shell, no network.
Pack a pull request into one markdown file optimized for LLM code review.
自进化软件质量系统 — 扫描器+修复器+DAG管道+经验积累+成本熔断
CRASS is a full-stack web application built with React.js & Supabase for AI-powered code review & security scanning. Features project uploads, real-time AI suggestions, security reports, analytics dashboards, and a sleek, responsive UI.
GitHub Action that automatically reviews pull requests using AI (OpenAI / Anthropic)
AI-powered CLI for structured repository audits with Codex or Claude Code, including evidence packs, risk findings, roadmap reports and parallel analysis.
Audit legacy codebases with adversarial AI agent teams — 7 iterations, 168 findings, 81.8% reliability score
Scan multi-language projects using AI to detect and fix technical debt, security issues, and documentation gaps without external dependencies.
The human-in-the-loop for AI coding, automated. Catches when your agent lies, leaves typos, or skips work — verifies every turn against the real diff, then makes it run, screenshot & self-fix before finishing. Claude Code hook + CLI.
gradio region:us
An AI code review system that analyzes code for bugs, security issues
A precise dependency analysis tool for npm and pnpm projects
An open source AI PR reviewer built from many narrow lenses and one careful curator
Structured code-level review of open-source AI agent projects
Yang Code Review (YCR) - A lightweight GitHub Action for AI-powered, OWASP-aligned code review with your own LLM provider.
🤖 Multi-agent AI code reviewer & documentation generator powered by CrewAI, Google Gemini 2.5 Flash, and Streamlit.
Code Turtle "🐢" is the open-source AI code review platform that helps teams ship better code with intelligent pull request reviews, inline feedback, and noise-free re-reviews 🚀
Relay code changes through isolated plan, build, review, and fix tasks in Codex App.
Auditable repository maintenance AgentTeam with evidence-backed pull requests, automated code review, and human approval gates.
自托管的多 Agent PR 审查工作台:GitHub 只读接入,审查发现与验证证据汇集 Console,合并由维护者决定。Developer Beta。
docker openenv region:us
Autonomous BareBone Harness that Audits your complete codebase
One model writes the work, a different one reviews it, and neither decides whether it passed. Cross-provider AI review with verifiable evidence, for DeepSeek Harness/Cordis hosts. 中文文档见 README.zh.md。
SKILL.md-standard proofreading skill — code & document review with real, verified formal-verification backends for C, Python, Rust, Java, and C++
YieldPoint
Whole-repository code review by AI agents: blocks, a coverage map, hypotheses with verdicts, four roles. An Agent Skill.
Two AI models build it; the harness checks the rules. fix/add/refactor/build/plan where tests are replayed against the original code — for Claude Code, Codex, Gemini CLI, Antigravity, OpenCode and Cursor. No API keys.
Self-hosted AI code reviewer for GitHub pull requests. DeepSeek-V4 + Blackgeorge multi-agent pipeline posts diff-anchored findings with severity badges and suggestions. Runs as a GitHub Action or your own GitHub App. BYOK.
Ruthless automated code review for any tech stack. 31+ frameworks, post-mortem verification, game dev support, anti-AI-slop detection.
Autonomous, self-hosted AI code reviews, calibrated scoring gauges, and merge gates from any open model.
VSCode extension that provides verification for files including auto-generated code
Universal AI code review tool supporting ANY OpenAI-compatible API (DeepSeek, Qwen, OpenAI, Groq, Ollama, LM Studio). Multi-agent pipeline with review → fix → test → verify workflow.
Multi-agent AI code review · Model-agnostic · 90%+ recall on synthetic eval set with DeepSeek/GPT
🔪 Surgical AI for your codebase. Diagnose. Assemble. Operate. Zero side effects.
Eight constrained reviewers. Each scoped to a different failure surface. Hook-enforced walls, not just prompts.
AI-powered Staff Engineer. Automate architectural reviews, debt scanning, and multi-file migrations.
This work is based on @RepoAudit, an autonomous AI agent for bug detection. Check the master branch.
AI-powered local code review tool & MCP Server. Works with GitHub Copilot & Claude to catch bugs, find secrets, and generate commit messages before you push. 100% Local & Private.
Let your claude-code get second opinion and review cc execution results from Deepseek
An interactive Human-in-the-Loop (HITL) review tool for Claude. Opens a local UI to 'redline' specifications and plans before code is written.
An autonomous LLM-powered agent that reviews GitHub Pull Requests fetches diffs, analyzes code changes, and returns structured feedback with severity ratings and interactive visualizations.
Production AI code review + autonomous web research agent. Claude tool-use loop over 4 Bright Data products (Web Unlocker · SERP API · Scraping Browser · MCP Server). HubSpot CRM hub, Lead Brief in Telegram with freshness buckets. Oracle Cloud free tier, $0/month, solo founder.
Multi-Agent Code Evolution Platform — debate-style review with health scoring, tech debt tracking, architecture analysis, and improvement roadmaps
Privacy-first autonomous code review agent powered by LangGraph, RAG, and local LLMs that analyzes repositories and produces reports and code fixes. (no cloud, no APIs.)
Compare code reviews across models in Claude Code with ranked todos and subagent dispatch via MCP.
Agent 说'明白了'——你的请求它真的看懂了吗?FindGap 在你按 Enter 前找出会导致返工的 gap。Trust Chain 第一节点。
A coding agent in 5 files, plus a skeptic that catches it faking the fix — verify AI code with a check the agent never saw. Runs on any model (OpenRouter/OpenAI/Ollama).
Decision governance for code and the agents editing it — track PRD→ADR→SPEC decisions, map them to files, and gate changes against them. Deterministic, honest CLI + MCP.
AI-powered code review and autonomous development platform built with TypeScript, React, FastAPI, PostgreSQL and LLM-based agents.
Command a fleet of AI agents — one-command installer + risk-tiered review gate. GitHub & GitLab.
Self-hosted GitHub review bot for your public and private repos — its own App identity, ~$0/mo on free-tier LLMs + Cloud Run.
PR and Code Understanding. Not just approval.
Stops your coding agent from pushing unverified work. Your agent does the reviewing; a state machine records the result per-commit and gates the push.
Automated detection of atomicity violations in large-scale systems
Codex-native Claude review plugin for read-only, evidence-cited Opus review lanes.
Governed, auditable AI review platform: the review and approval work a team does by hand, as a webhook-triggered LangGraph agent with human-in-the-loop approval, Langfuse tracing, an eval-gated CI pipeline, and a tamper-evident hash-chained audit trail. Provider-agnostic (mock/Anthropic/OpenAI), FastAPI, Bicep IaC for Azure Container Apps.
Governance layer for multiple AI coding agents on a production codebase: constitution, decision log, evidence grammar, CI gates.
Autonomous AI code review & PR automation — a self-hosted, multi-agent software factory that reviews, fixes, and merges its own pull requests through a verifying LLM pipeline.
Agentic AI code review for GitHub Pull Requests via opencode. Structured, project-aware, remembers previous passes. Works free, no API key required.
Multi-agent validation for any repository: independent theses, adversarial critics, and a seal whose verdict is computed from real command exit codes — never from an agent's prose. One body, three runtimes: DeepSeek Harness, Claude Code, ZCode.
A stealthy, high-performance AI Chrome Extension that provides instant code analysis, bug detection, and intelligent explanations via NVIDIA's Llama API. Zero DOM injection. Pure productivity.
Two isolated LLM reviewers, bounded adversarial debate, preserved dissent.