Coding agents & developer tools

Code review agents

922 agents · most starred first

Code review agents, page 6 of 10

pr-commentor★ 5

Generate AI-powered PR summaries and titles directly inside GitHub comment boxes. Supports Claude and OpenAI.

md-feedback★ 5

Browser-first markdown plan review. Start local web review in one command, then let your agent continue through MCP.

coherence★ 5

Drift detector for agent-assisted repos: catch stale docs, ADRs, tests, metrics, and generated artifacts.

anti-vibe-skills★ 5

As vibe coding makes AI-generated output cheaper and more abundant, the scarce resource becomes developer judgment. These skills are judgment trainers.

bouncer★ 5

Gemini stands at the door. Independent quality gate that audits Claude Code's output before it can stop.

ai-pr-reviewer★ 5

Automated PR reviews powered by AI. Plug into any GitHub repo in minutes. Supports Groq, Gemini, Anthropic, and OpenAI with multi-provider fallback and key rotation. Get actionable, context-aware code feedback on every pull request without slowing down your team. Zero dependencies beyond requests.

wcag-accessibility-agent★ 5

WCAG 2.1 accessibility agent built on Anthropic API. Audits, evaluates and fixes digital products for UX, UI and development teams. Includes an installable Skill for Claude.ai and a full CLI with PDF/DOCX export.

elenchus-mcp★ 5

Elenchus MCP Server - Adversarial verification system for code review

DebtGuardianAgent★ 5

The agentic DebtGuardian codebase for the IPN project TechDebtOps

antfleet-core★ 5

The trust layer for code written by agents. Two frontier models, unanimous review, SHA-pinned receipts.

aido★ 5

The AI companion for the pull requests your AI writes. Review, summarize, explain, document, test & triage PRs and issues from a comment (aido <command>) or automatically on AI-authored PRs — with Gemini, ChatGPT, Claude, or any OpenAI-compatible model (Mistral, DeepSeek, …). BYO key, no third-party data processor.

fresh-eyes-review★ 5

Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests

quality-assistant-prototype-03★ 5

Quality engineering for agentic coding workflows — a quality team member for Claude Code that observes, analyzes, and nudges, never blocks.

bug-shepherd★ 5

MOVED: now the bug-shepherd plugin in github.com/mshadmanrahman/pm-pilot. Install: claude plugin install bug-shepherd@pm-pilot

heimdall★ 5

Verification gates for AI coding agents — nothing ships unproven. Falsifiable oracle gates, team wall, receipts. Works with Claude Code today; Cursor, Codex, Gemini CLI & every git repo next.

rabbitai★ 5

Open-source AI code reviewer that auto-reviews GitHub PRs LangGraph agents, knowledge graph blast-radius detection, mem0 persistent memory Zero cost, self-hostable.

checkyourself★ 5

Local-first completion-evidence system for AI-built apps: read-only audit, verifier-executed challenges, evidence-based 0-100 score, guided fixes, learning plan, CLI, and MCP.

invariant★ 5

Consequential analysis for automated review of codebases and pull requests

redline★ 5

Review mode for LLM-generated plans — Google Docs-style commenting on any .md file

tour★ 5

Local code review at AI speed — TUI + webapp over a pinned git diff.

pr-pilot★ 5

GitHub Action + CLI that auto-writes PR descriptions, adds labels, and reviews code using OpenAI

nit★ 5

Local AI code review agent. Self hosted with Ollama, no data leaves your machine.

superpipelines★ 5

Loop Engineering for AI coding agents, with real review boundaries. Your AI reviewer cannot edit code. Structurally.

skills★ 5

Drop-in skill for aislop — the engineering standards layer and quality gate for AI-written code. Install via 'npx skills add scanaislop/aislop-skill'.

glassbox-ai★ 5

🔮 Turn any AI-written code change into a gamified, interactive walkthrough, gaming experience

claude-friends★ 5

Claude has friends. On the calls that matter it asks AIs from other families — Gemini, a fresh-eyes second Claude, optionally GPT — who catch the blind spots one model can't see alone.

DontPanic★ 5

Keep AI coding agents honest. DontPanic is a vendor-neutral meta-harness that makes agents work to a locked plan, has a second model check the work, and asks a human before risky steps — with circuit breakers, a local operator console, and a full evidence trail.

code-review-agent-mcp★ 5

AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.

agent-complexity-optimizer★ 5

Scan any codebase for O(n²) hotspots, N+1 queries, and complexity issues — works with 13+ AI coding agents

vibe-council★ 5

A local multi-model council for developer workflows: review plans, critique diffs, extract decisions, and keep project-local AI decision memory.

dev-workflow-kit★ 5

Claude Code plugin: spec-driven agentic coding with cross-model review gates (Claude builds, Codex reviews), a self-hardening findings ledger, and repo-enforced quality.

claim-plane★ 5

Claim Plane — the control plane for verifiable AI engineering.

Graphora★ 5

The code knowledge graph that reviews your changes. Blast radius, risk memory from git history, and 82-94% fewer prompt tokens. Zero Docker, no LLM to build, 11 languages

tellur★ 5

Local-first AI code provenance: line-level attribution, PR risk reports, policy checks, and tamper-evident audit trails for AI-assisted software.

arch-optimize★ 5

Architecture optimization skill: six decay risks (R1-R6), quality metrics, regression guard. Five stdlib-only Python scanners, zero dependencies. Architect-programmer dual-agent workflow.

adc★ 5

Structured decision comments (ADCs) for agent-written, human-reviewed code.

proofloop★ 5

Universal quality evaluation plugin for Claude Code — 7-dimension scoring (correctness, completeness, adherence, efficiency, safety), configurable rubrics, threshold blocking, auto-hooks & /judge command.

AI-Codereview-Gitlab-Opencode★ 5

AI code review for GitLab, GitHub, and Gitea with OpenCode Agent Review backend. 基于 sunmh207/AI-Codereview-Gitlab 演进的 OpenCode Agent Review 版本,保留原有多平台 AI Code Review 能力,并新增 OpenCode Serve backend 集成。

code-review-adversarial★ 5

Adversarial multi-agent code review — a committee of specialist reviewers that catches what single-pass AI review misses.

spec-sync★ 5

📐 Bidirectional spec-to-code drift detection. Rust CLI and MCP server that catches undocumented exports and vanished symbols in CI.

bearing★ 5

An intel layer for AI coding agents that assumes its own rules might be wrong — and keeps the evidence. Authoritative north-stars the agent must cite, a task-core written before compaction eats it, review by an expert in YOUR domain, and an installer that verifies its own claims instead of printing success. Claude Code, Cursor, Zed, Codex.

code-factory★ 5

Evidence-first audits for AI-generated code: prove tests can fail, catch security and release gaps, and ship reviewable receipts across VS Code, JetBrains, CI, MCP, and App Store workflows.

autonomous-agents★ 5

A curated collection of autonomous AI agents for systematic codebase improvement. Each agent specializes in a specific domain—performance, security, UX, testing, etc—making focused, incremental changes while maintaining strict safety protocols. Inspired by Google Jules, these agents work to enhance code quality through targeted micro-improvements.

doubt.nvim★ 5

Neovim plugin for code review with inline claims, persistent sessions, and exportable handoffs to AI agents..

prism-reviewer★ 5

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.

katamari★ 5

Terminal diff review with real LSP and stacked-PR-like review units — hover, go-to-definition, diagnostics, comments an AI agent can read back and resolve, and a big tangled diff regrouped into ordered review units by your own agent CLI. git and jj.

Godmode★ 5

Your coding agent says "done." Godmode is how you know: a local, tamper-evident evidence ledger of what it did, claimed, and verified - with gates and a completion bar enforced in hooks at runtime. Zero deps, zero network. Claude Code, Grok, Codex, OpenCode, Antigravity.

nullius★ 5

Most tools check the code your agent wrote. nullius checks how it got there — citations, session journals, weakened tests.

disensor★ 5

Adversarial AI code review that declares what the round could not close. Python CLI + GitHub Action, MIT.

push-skill★ 5

A Claude Code skill that checks a branch the way a careful reviewer would, then pushes it. Two adversarial model reviews, a blocking security pass, a coverage gate, and a live run. No dependencies.

notabene★ 5

Leave notes in the margins of your repo's docs then let your AI agent apply them, resolve the threads, and journal what changed & why.

rvw★ 5

Layered, replicated, self-adjudicating code review orchestrator

policyNIM★ 5

PolicyNIM is a policy-aware engineering preflight layer for AI coding agents.

logicprobe★ 5

设计与代码的声称核验:事实类对照源码,行为类跑可执行模型;含结构/依赖审查(单层与多粒度细化)、UML 审查、基线对比与导出。dsh 原生工具 + 多平台 Agent Skills。 | Claim, architecture and behaviour verification for designs and code — facts against the source, behaviour as models, plus structure review, UML review, baseline diffs and exporters.

objection★ 5

OBJECTION! A skill and plugin for AI coding agents (Claude Code, Codex, Cursor, Gemini): accusers, a defender and a judge review the PR, and a gate blocks it until APPROVED.

gpt-pro-audit★ 5

Agent skill that audits code and plans with connected GitHub context and a strong ChatGPT model using Effort Pro through Chrome.

jevkit★ 5

Fast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay

Java-Claude-Skills★ 5

Claude Code skill: review and modernize legacy Java 8 code to Java 21 with AI. Generates a 1-100 score. Specialized for financial systems.

mergepath★ 5

A repository standard that makes AI coding agents reviewable: canonical docs every agent must read, 70+ fail-closed CI checks, multi-identity review so no agent approves the PR it wrote, automated external review, and one-command propagation to every downstream repo.

repoguard★ 5

The Architecture Guardian for AI-assisted code. Generate strict .cursorrules and audit PRs.

engineering-intelligence★ 5

Stop AI agents from shipping bad code. Deterministic architecture, security, API, database, and UI quality control for coding agents.

countershape★ 5

A completed autonomous AI build: an agent built this month-long project on its own under a verification discipline where every commit carries cryptographic receipts of what actually ran. All ten units sealed; builds and runs on one tested macOS profile.

chock★ 5

Quality gates for Rust: new code must be clean, and old debt has a limit that each fix lowers.

mergegate★ 5

Local code review hub for AI coding agents (Claude Code, Codex, Cursor, opencode). Agents submit with one CLI, you review files ranked by importance, feedback flows back. GitHub or plain git.

eyeful★ 5

Multi-agent code review with executable evidence

whiteboard-defense★ 5

Know what your AI agent built, and where it just used its defaults. A skill + plugin for Claude Code, Codex and OpenCode that briefs you on decisions, provenance, and failure modes so you can pass the whiteboard defense.

code-hawk★ 5

Automate code review workflows with advanced AI analysis. Get intelligent insights on pull requests, track coding activity, and improve code quality at scale.

codeality★ 5

A++ clean code from your AI agents. Zero effort for you, fewer tokens for them. Gates for TypeScript, Python, Rust, UI, databases and tests.

wingdiff★ 5

Understand a pull request before you approve it. A free, local guided review: every claim linked to the diff, no bot comments, you publish the review.

design-review★ 5

Claude Code skill: scored UX critique with Before/After/Why fixes and Nielsen/WCAG citations

tribunal-kit★ 5

A universal, native-Rust governance layer for AI coding agents. Enforces Subagent-Driven Development (SDD) to stop hallucinations before they hit disk.

Camelot.skill★ 5

⚔️ AI 代码审查 Skill —— 自动挑刺、定级、给下一轮指令,让 agent 交活前自己把关。

emetgate★ 5

A deterministic verification kernel between LLM agents and your source tree. The model proposes, the kernel verifies.

herdr-kanso★ 5

Your agents in a row, not a grid. A Herdr layout: terminals keep their width, a PR's feedback starts an agent, your editor is one key away.

harness-engineering-audit★ 5

Codex skill for evidence-linked repository harness audits, scored assessments, and prioritized engineering fixes.

review-pro★ 5

Repository-aware AI code review for coding agents — triage → 13 specialist reviewers → synthesis. Reviews what the agent changed and what the repo already knew. Claude Code, opencode, Cursor, Codex.

featspiration★ 5

Agent skill: review outside projects against yours and get a findings page with one copy-ready prompt per feature

orbit★ 5

Your backlog drives your agents. Linear, Claude Code and code review in one native macOS app. Fork it and make it yours.

prmate★ 4

AI buddy that reviews your GitHub Pull Requests.

AI-Code-Reviews-using-Langchain-Ollama-and-Streamlit★ 4

An AI-powered code reviewer supporting multiple programming languages, including: Python, JavaScript, Ruby, Java, SQL

CodeElevate-AI-Code-Reviewer★ 4

Developed a web application utilizing Streamlit, LangChain, and OpenAI's GPT model, designed to analyze, review, and enhance code quality, providing users with intelligent feedback and optimized code solutions.

capybara★ 4

AI-powered VSCode extension that uses LLM technology to provide insightful suggestions into code quality.

sap-atc-checker★ 4

SAP ATC Checker - Run ABAP Test Cockpit checks with any check variant via SAP ADT API

copilot-pr-review★ 4

This is a tool that combines LLM model's capability with GitHub action in CI Pipeline to improve development efficiency and quality.

ad-ai-pr-reviewer★ 4
SiftPR★ 4

An agentic PR review assistant

pr-review-agent★ 4

Multi-agent PR reviewer on LangGraph — four specialists (security, performance, tests, quality) review in parallel. Self-hostable, model-agnostic. GitHub Action + CLI + Python library.

ghagga★ 4

AI code review that learns your project — GitHub App, Action, CLI & self-hosted. 17 static-analysis tools (Semgrep, Trivy, Gitleaks, Ruff…), persistent review memory, multi-agent orchestration, SARIF export.

PatchPilot★ 4

Code Quality Guardian

codepause-extension★ 4

VS Code extension to track AI coding assistant usage and maintain code quality. Works with Copilot, Cursor, Claude Code & more. 100% private, local data.

tokentoll★ 4

Catch LLM cost changes in code review. Infracost for LLM spend.

probe-extension★ 4

AI-powered code review companion for GitHub PRs

challenge-plans★ 4

Agent skill + CLI for multi-agent adversarial review of plans & specs before you execute them. Runs on the Claude Code / Codex subscriptions you already have — no API keys.

sap-atc-checker★ 4

SAP ATC Checker - Run ABAP Test Cockpit checks with any check variant via SAP ADT API

AI-for-ISO-19650★ 4

Multi-agent Claude Code system for auditing BIM documentation against ISO 19650

hydra★ 4

Multi-perspective code review council for Claude Code. 3 advisors by default, 10 agents in deep mode (Opus + Codex). Evidence chains, adversarial self-test, dual-path verdict. Based on Karpathy's LLM Council.

closedtab★ 4

Review the work your AI agents do. CLI + MCP.

safe-review★ 4

AI 辅助编程的安全与测试回归审查 Skill,分清主次守住权限/数据/核心业务风险 | Security & test-regression review skill for AI-assisted coding — triages auth, data-ownership & core-business risks

assisted-review★ 4

assisted-review fetches a PR or MR and presents it one hunk at a time in a focused browser UI

own-your-diff★ 4

Own Your Diff is a local human review gate for AI-assisted code changes. It generates grounded multiple choice questions before agents can push or open pull requests.

More in Coding agents & developer tools