Coding agents & developer tools
Code review agents
922 agents · most starred first
Code review agents, page 5 of 10
Converge — Dual-agent iterative convergence for plan/code review | 双 Agent 迭代收敛器,用于计划与代码的对抗式审查
Marj — Make Claude's memory an expansion of your memory. Review local git changes in a GitHub-style UI and talk to your Claude Code session in the diff.
Your coding agent. Your changes. One terminal. A live review workspace for Codex and Claude Code, built in Go.
Minimal webapp for local code review of branches
Evidence-driven assurance for autonomous coding agents.
AI-assisted OSS maintenance you can verify — triage issues, reproduce bugs, review PRs, check regressions and security, and prepare releases with humans in control.
AI harness for EasyEDA Pro — offline schematic/PCB design review, live bridge (daemon + editor extension), review-to-local-edit with verified persistence
Keep the agent honest: a plain-English linter for Markdown prose and code comments.
An independent multi-model code reviewer that remembers the codebase between sessions
Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.
Automated 3-layer design review and linter for KiCad (DRC/ERC, spatial heuristics, multimodal vision AI, and native MCP server)
Human-approved engineering decisions for AI coding agents. Local-first MCP tools for Codex and Claude Code with evidence-based Git diff reviews.
Reviews what your coding agent did, not just the diff: did it do what you asked, what it decided on its own, and what is wrong in the code.
Review a diff beside your coding agent in Rex, and send comments on its lines straight into the agent's prompt.
Swarming your messy diffs before they reach production.
GitHub Action for generating code review brief using ChatGPT AI (gpt-4, gpt-3.5-turbo model)
Have AI Linus Torvalds swear at your patches
Validation-First Workflow (VFW) for AI-assisted development
A Paperclip plugin for browsing and reviewing files linked to issues — built entirely by AI agents
Lifecycle-shaped Claude Code agent kit: scheduled audits → ready-state issues → developer-agent PRs → multi-persona advisory review. Six named PR reviewers, five audit scanners, one installer. Claude-only by design.
Code review for jj (jujutsu) workflows: revset-defined reviews, patchset-anchored comments that survive branch movement, with web, HTTP, and MCP surfaces for fast AI-agent iteration.
Every shortcut your coding agent takes, saved to your repo as it happens. Fix them when you're ready.
Audit repositories for AI coding agent readiness.
Code review, but with 5 models arguing first.
A peer-review protocol for AI models. Claude, Codex, Gemini and others review each other's code via CLI handoffs. Bidirectional, symmetric, opensource.
Local-first GitHub agent loop that reviews PRs, opens patches, and repairs feedback with your coding CLI.
A deep, multi-angle, adversarially-refuted code review skill for Claude Code, Cursor, and other coding agents
Native macOS Markdown viewer and rendered-diff reviewer for documentation-heavy GitHub PRs (design docs, ADRs, skills, runbooks)
Independent parallel code reviews with multiple AI agents, verified by one orchestrator.
Agentic development · automated review · a full record - Coding agents build your change. An independent principal-engineer agent reviews it. Only commits that earn a hallmark leave your machine.
Skills that turn AI code reviews into decision reports. You review the review, then decide.
Agent skills to police AI-generated frontend work for design system conformance.
Open-source agentic coding and code-review harness with multi-model support, tool execution, skills, approvals, and clear terminal workflows.
Spin up 200 parallel Claude Code agents to audit your codebase with thoroughness a single agent can't achieve.
Code review agents, scripts, and workflows.
AI-powered code review framework for Claude Code - Detects 40+ issue types across 10 categories
Claude Code plugin providing AI-powered agents for code auditing, research, and multi-model consultation (OpenAI Codex, Google Gemini)
A copilot for AI coding agents — read-only supervision for Claude Code & Codex: re-entry recaps, safety verdicts, grounded chat, every claim cited.
Autonomous multi-agent AI pipeline that reviews GitHub pull requests, generates fixes, runs test validation, and produces documentation.
A cross-agent consultation bus: a CLI coding agent asks a different-provider agent for a second opinion — one advisor, or a multi-agent council that audits code and verifies every finding against its file:line. 12 agents: Claude, Codex, Gemini/agy, Grok, OpenCode, Hermes, Kimi, Cursor, Kilo, Cline, Goose, Pi.
Agentic code review CLI — LangGraph orchestrates 13 deterministic static analyzers (oxlint/bandit/clippy/spotbugs/golangci/cppcheck) + LLM reasoning across 23 languages including industrial PLC. Grounding validator kills hallucinated paths. RAG over your guidelines. dedup --fix actually edits files with multi-step undo (no git required).
A maintainability ratchet for AI-assisted Python.
Free & open-source MISRA C / CERT C / BARR-C compliance for embedded C — the vendor-neutral alternative to Polyspace, Helix QAC & Coverity's paid workflow. Agentic fix loop + MISRA Compliance:2020 audit evidence, from any IDE via MCP.
A CLI tool that leverages AI (Claude Code CLI or OpenAI API) to automatically review pull requests across GitHub and Azure DevOps, enforcing coding standards from configurable rule files
Agentic AI code review for GitLab MRs and GitHub PRs, with the LLM of your choice. Posts only actionable findings as inline review threads.
DeepSeek Harness web plugin: inline +N −M diff badges on edit/write tool rows and a per-turn file change summary card. Scroll-windowed diffs, PTC/code-dispatch fallback, undo — no git required.
Agent skills, including blind multi-model code review: Codex, Gemini, Grok and Claude review the same packet without repo access
Autonomous AI code-review agent for .NET microservice fleets.
🦨 Stop shipping smelly code. 120+ named code smells with before/after examples across C, C++, C#, Java, Python, Go, Rust, JavaScript, TypeScript & SQL — an AI agent skill that improves code quality during both development and code review.
🤖 Scribe is a simple pull request agent that writes your PR descriptions
An AI tech lead in server form—this intelligent MCP agent validates your coding agent's strategy, analyzes impact, and catches critical issues before any code is written. Like having a senior engineer review every approach, ensuring thoughtful architecture and fewer regressions.
codex-review skill
A code review AI assistant that suggests improvements in the provided code
Every PR is a learning moment. sphinx-ci generates a quiz from your actual diff — so you ship code you truly understand.
Code Guardian enforces architectural rules in your codebase, especially valuable when working with AI-generated code. It validates changes against your defined standards to prevent violations and reduce AI hallucinations.
Comprehension-driven development: Claude quizzes you on your own PR diff so you catch the gap between what you think your code does and what it actually does — before you merge.
Cross-examination protocol for multi-LLM CLI sessions — blind claims, command-verified debate, git-diffable bus. Zero-dep single-file Python.
redteam is a multi-model harness that forces an independent reviewer to challenge AI-generated code before it ships. Apache-2.0.
gradio region:us
Hope helps people take on more complex work with AI while preserving their judgment and agency.
Publish, share and comment on the HTML and Markdown your coding agent writes. Self-hosted.
A lightweight framework for agent-driven software delivery
A governance layer for AI coding work — not an orchestrator. Seven gated roles with typed submissions, independent audit seats, and deliberately no runner: composition stays with the caller.
Claude skill that audits and builds web UI: measures the render at 360, 768 and 1280px with a Playwright script, scores 16 categories, catches the alignment and consistency faults AI tools ship, and raises landing pages, dashboards and analytics reports to exceptional.
Help AI assistants plan, write, review, and explain Linux kernel patches, making kernel changes safer, clearer, and easier to get ready for upstream.
Convergent deliberation loop for coding agents: multi-pass, coverage-gated, append-only ledger review and planning. Claude Code, Codex, OpenClaw.
HighReview is a powerful local PR review tool that doesn't disrupt your working environment. Using Git Worktree, it provides IDE-level code analysis and AI insights without touching your current working directory.
Deep-dive code analysis agent skill by Anivar Aravind — contributor reviews, codebase governance, promotion readiness.
Dual-agent AI code review loop — consensus at every step, not after the fact. Used to evolve an open-source fork into a production AI assistant with zero manual code.
AI-powered PR reviews using your own LLM API key (Anthropic, OpenAI, Gemini)
Argus - Multi-agent code quality & architecture review plugin for Claude Code. Runs parallel analysis agents with cross-validation to catch real issues, not false positives.
Learn from PR reviews, help your team proofread faster and more efficiently with LLMs.
Archived: use Claude Code’s built-in /simplify. Sonnet routing and migration instructions in README.
Code review that cites its lines or stays silent. Local-first, non-agentic, grounded in the diff.
Quality-first harness for autonomous AI coding agents — deterministic gates + a default-FAIL evaluator over a Beads task spine. Claude Code plugin; done is earned, not asserted.
This repository contains information about issues we are working on and allows all of you to give direct feedback.
gradio smolagents agent smolagent tool agent-course region:us
JetBrains/PyCharm plugin to review an agent's changes in your IDE and relay batched, line-anchored comments back into its running session — instead of retyping feedback into the terminal.
Portable Agent Skill for small, verified coding-agent changes
Autonomous multi-agent AI system for intelligent GitHub PR review and bug detection. Built with LangGraph, RAG + tree-sitter, and GitHub MCP for deep codebase understanding. Automatically raises issues, drafts fixes, and opens PRs as smart-pr-review-bot[bot]. Supports Review Only, Human-in-the-Loop, and Auto-Pilot modes with full LangSmith tracing.
LLM-assisted code auditing. 54 phases, custom overlays, accountability.
Quorus AI: multi-agent rooms for Claude Code, Codex and opencode. Agents fix in their own git worktrees, review each other and push to your repo. MCP + CLI, MIT.
Mission control for AI coding agents: every PR on the architecture map, an MCP server, a tamper-evident record of who decided what, and which branches in flight will collide.
Prevents AI assistants from suggesting outdated Rust code patterns
AIに任せきりでは、意図通りの実装は実現しない。AIエージェントのリードを取り戻すためのデスクトップアプリ。
Repo-level AI coding readiness assessment, in Go. Maps a repository to its level on the AI Codebase Maturity Model (ACMM).
Bilingual agent workflow contracts, PR review templates, and sync automation for AI-assisted development
An advanced AI-driven code analysis tool built with Next.js, leveraging OpenAI's API to review and debug code efficiently.
Cross-layer static analysis of Go source code, scripted in Scheme
🧜♀️Iara is an automated, project-agnostic, and configurable code review tool designed to run in CI/CD pipelines or locally via CLI. It uses the OpenRouter API to access various LLM models (Llama 3, Gemini 2.0, etc.) for free or through paid plans.
MergeGate: deterministic execution protocol for AI-assisted development and the execution layer for GitNexus-style code intelligence
🤖 Multi-agent code review framework using CrewAI. 7 specialized agents analyze PRs with evidence-based findings, auto-patches, and comprehensive evaluation metrics.
Multi-stage, multi-agent AI code review for GitHub — self-hosted, provider-neutral. A planner picks the team, agents review in parallel, a judge filters the noise.
Review your GitHub PR queue with Claude Code, from a TUI
A bot designed to seek out and provide feedback about potentially bad reviews.
🤖 AI-powered code review CLI tool that leverages LLM to analyze pull requests, generate detailed reviews, and create PR descriptions. Supports multiple review modes, git diff analysis, and markdown-formatted outputs.
Local-first AI code review CLI. Reviews git diffs, commits, ranges, and PRs using Anthropic, OpenAI, Gemini, or Ollama. Outputs text, JSON, SARIF, and Markdown. Pre-commit hooks, caching, multi-model compare mode, and CI-friendly exit codes.
This GitHub Action uses AI models from OpenAI and Anthropic's Claude 3 to automatically generate formatted and insightful content for pull requests based on code changes.
AI Code Review with GitHub Actions
LLM Powered Code reviewer