{"id":125818,"url":"https://github.com/kodustech/awesome-ai-code-review","name":"awesome-ai-code-review","description":"Awesome list of AI Code Review agents, copilots, and research papers.","projects_count":54,"last_synced_at":"2026-07-25T13:00:29.072Z","repository":{"id":340794591,"uuid":"1118282543","full_name":"kodustech/awesome-ai-code-review","owner":"kodustech","description":"Awesome list of AI Code Review agents, copilots, and research papers.","archived":false,"fork":false,"pushed_at":"2026-06-28T21:35:05.000Z","size":38,"stargazers_count":35,"open_issues_count":2,"forks_count":23,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-07-06T19:03:15.746Z","etag":null,"topics":["ai-agents","ai-code-review","ai-pull-request-review","automated-code-review","awesome-list","code-quality-ai","code-review","developer-tools","llm","llm-code-review"],"latest_commit_sha":null,"homepage":"https://aicodereviews.io","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kodustech.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-17T14:23:07.000Z","updated_at":"2026-07-06T16:17:47.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/kodustech/awesome-ai-code-review","commit_stats":null,"previous_names":["kodustech/awesome-ai-code-review"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kodustech/awesome-ai-code-review","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kodustech%2Fawesome-ai-code-review","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kodustech%2Fawesome-ai-code-review/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kodustech%2Fawesome-ai-code-review/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kodustech%2Fawesome-ai-code-review/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kodustech","download_url":"https://codeload.github.com/kodustech/awesome-ai-code-review/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kodustech%2Fawesome-ai-code-review/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35879604,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-07-25T02:00:06.922Z","response_time":64,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2026-03-30T11:00:50.602Z","updated_at":"2026-07-25T13:00:29.072Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["License","IDE Assistants \u0026 Copilots","Security \u0026 Static Analysis AI","Benchmarks","Key Research \u0026 Papers","CLI \u0026 Local Workflows","Automated PR Agents"],"sub_categories":[],"readme":"# Awesome AI Code Reviews [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\nA curated list of AI-powered tools, agents, and platforms dedicated to automating code reviews, enforcing guidelines, and improving software quality.\n\n\u003e **Maintainer Note:** This list is curated and maintained by the engineering team at **[Kodus](https://kodus.io)**. We love open source and building better devtools.\n\n## Contents\n\n- [Automated PR Agents](#automated-pr-agents)\n- [IDE Assistants \u0026 Copilots](#ide-assistants--copilots)\n- [Key Research \u0026 Papers](#key-research--papers)\n- [Security \u0026 Static Analysis AI](#security--static-analysis-ai)\n- [CLI \u0026 Local Workflows](#cli--local-workflows)\n- [Open Source Models](#open-source-models-for-code)\n- [Benchmarks](#benchmarks)\n\n---\n\n## Automated PR Agents\n\n_Tools that connect directly to GitHub/GitLab to review Pull Requests, comment on code, and suggest fixes asynchronously._\n\n_Note: This list is not intended to compare tools; as maintainers of Kodus, we are biased._\n\n- **[Kodus](https://kodus.io)** (⭐ _Maintainer_)  \n  An AI code review agent focusing on high-signal feedback. It allows teams to define custom review guidelines (using plain English) to enforce architectural patterns and best practices, reducing noise in the review process.\n\n- **[CodeRabbit](https://coderabbit.ai)** Provides line-by-line feedback on pull requests and generates summaries of changes. Features a chat interface within the PR to discuss the feedback with the AI.\n\n- **[Git AutoReview](https://gitautoreview.com)** VS Code extension that reviews pull requests using three AI models (Claude, GPT, Gemini) to catch bugs, security vulnerabilities, and performance issues. Supports GitHub, GitLab, and Bitbucket — the only tool covering all three platforms from inside the IDE.\n\n- **[Greptile](https://greptile.com)** An AI engine that indexes the entire codebase to understand context. It focuses on answering complex questions about the repo and reviewing code with full-repository awareness.\n\n- **[Zenable](https://zenable.io)** AI guardrails that learn your team's standards and ensure coding agents follow them. Works across IDE (via MCP), pre-commit, and PR review to catch bugs and security issues in AI-generated code in real-time.\n\n- **[Cursor Bugbot](https://cursor.com/bugbot)** AI-powered PR review that runs automatically to catch real bugs and security issues with a low false-positive rate.\n\n- **[Revieko](https://synqra.tech/revieko)** - Repo-specific architecture drift detection in pull requests (structural risk + hotspots).\n\n- **[Polarity](https://www.polarity.so)** - The First AI QA Engineer which does code review, testing, and long running agent tasks. Understands your entire codebase and code quality, zero fluff comments.\n\n- **[Conclave AI](https://conclave-ai.dev)** - A council of three models (Claude, GPT-5, Gemini) reviews each PR and, with a PRD attached, flags scope drift a diff-only review misses. Includes an autofix worker; self-hostable (FSL).\n\n- **[AI Change Passport](https://github.com/P-r-e-m-i-u-m/ai-change-passport)** - GitHub Action and CLI that creates signed provenance reports for AI-assisted pull requests, helping reviewers see sensitive files, dependency edits, workflow changes, and test coverage signals.\n\n- **[Ejentum agent-teams (adversarial-code-review)](https://github.com/ejentum/agent-teams)** Multi-agent code-review team built on the Ejentum Reasoning Harness. Reviewer agents call `harness_code` and `harness_anti_deception` as agentic tools during the review loop; each call returns a structured scaffold (named failure pattern, executable procedure, suppression vectors, falsification test) the agent reads internally before issuing review feedback. Catches false-confident approvals and sunk-cost framings that single-agent reviewers miss.\n\n- **[Gito](https://github.com/Nayjest/Gito)** - Open-source AI code reviewer for GitHub and GitLab. Runs locally via CLI or in CI/CD pipelines, and works with any LLM provider — including self-hosted models (Ollama, LM Studio, vLLM) for fully private reviews.\n\n- **[Ivy Tendril](https://github.com/Ivy-Interactive/Ivy-Tendril)** - Open-source AI coding orchestrator with automated verification gates (build, test, lint, format, AI review) that enforce code quality before any PR reaches human review. Orchestrates Claude Code, Codex, Antigravity, Copilot, and OpenCode.\n- **[Optibot](https://getoptimal.ai)** - AI code review for GitHub \u0026 GitLab that catches production-breaking bugs, business-logic errors, and security issues with line-specific feedback and optional inline fixes. The same engine also ships as a CLI, an MCP server, and a Claude Code skill.\n\n- **[Swarm Orchestrator](https://github.com/moonrunnerkc/swarm-orchestrator)** - GitHub Action and CLI that audits AI-generated pull requests for eleven cheat patterns (relaxed tests, swallowed errors, fake renames, and more). Advisory by default, with an opt-in merge gate.\n\n- **[heygrc](https://heygrc.com)** GitHub App that reviews pull requests against compliance frameworks (ISO 27001, SOC 2, GDPR, EU AI Act, and more), flags changes that put a control at risk, and says what to fix, citing the control clause.\n\n## IDE Assistants \u0026 Copilots\n\n_Tools that integrate with editors or local environments for autocomplete, chat, and agentic coding._\n\n- **[GitHub Copilot](https://github.com/features/copilot)** - The standard AI pair programmer for autocomplete, chat, and inline edits.\n- **[Cursor](https://cursor.com)** - AI-first code editor with built-in chat, autocomplete, and agent workflows.\n- **[Claude Code](https://claude.com/product/claude-code)** - Claude's coding agent for terminal, IDE, and web workflows that can manage large codebases and implement changes.\n- **[OpenAI Codex](https://developers.openai.com/codex/ide)** - OpenAI's coding agent that can read, modify, and run code, available as a VS Code extension with optional cloud delegation.\n- **[Google Antigravity](https://antigravity.google)** - Agent-first IDE with tab autocomplete, natural language commands, and cross-surface agents across editor, terminal, and browser.\n- **[Kilo Code](https://kilo.ai)** - Open-source agentic engineering platform with IDE/CLI support, tab autocomplete, and multi-agent orchestration.\n- **[Cline](https://github.com/cline/cline)** - Autonomous IDE agent that can create/edit files, run commands, and use the browser with user approval.\n- **[OpenCode](https://opencode.ai)** - Open-source coding agent for terminal, IDE, or desktop with multi-session workflows and broad model support.\n- **[SimpleReview](https://chromewebstore.google.com/detail/baiophhkajldflnpaaijgdigbkomkimm)** - Browser extension for in-browser visual code review. Hover any element on a live website, click \"Fix it\" to get AI-powered fix suggestions in a side panel.\n\n## Key Research \u0026 Papers\n\n_Fundamental reading on how LLMs are transforming software engineering._\n\n- **[AI-Assisted Assessment of Coding Practices in Modern Code Review](https://arxiv.org/abs/2405.13565)**: LLM-based system for enforcing coding best practices in code review.\n\n- **[Towards Practical Defect-Focused Automated Code Review](https://arxiv.org/abs/2505.17928)**: Automation pipeline for defect detection in C++ codebases using AI.\n\n- **[Automated Code Review Using Large Language Models at Ericsson: An Experience Report](https://arxiv.org/abs/2507.19115)**: LLM tool with static analysis for code review in industry.\n\n- **[DeputyDev -- AI Powered Developer Assistant: Breaking the Code Review Logjam through Contextual AI to Boost Developer Productivity](https://arxiv.org/abs/2508.09676)**: AI assistant for efficient code reviews to boost productivity.\n\n- **[CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review](https://arxiv.org/abs/2506.00296)**: RL framework for improving code review comment generation.\n\n- **[Leveraging Reviewer Experience in Code Review Comment Generation](https://arxiv.org/pdf/2409.10959)**: Integrating reviewer experience into AI models for comment generation.\n\n- **[A Survey on Machine Learning Techniques for Source Code Analysis](https://export.arxiv.org/pdf/2110.09610v2)**: Overview of ML applications in source code tasks including review.\n\n- **[BitsAI-CR: Automated Code Review via LLM in Practice](https://conf.researchr.org/details/fse-2025/fse-2025-industry-papers/24/BitsAI-CR-Automated-Code-Review-via-LLM-in-Practice)**: Practical LLM-based automated code review in large-scale environments.\n\n- **[AutoCodeRover: Autonomous Program Improvement](https://arxiv.org/abs/2404.05427v1)**: LLM for program improvement via code review and repair.\n\n- **[Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation](https://arxiv.org/abs/2411.10129)**: Fine-tuning LLMs with QLoRA for generating accurate code review comments.\n\n- **[Fine-Tuning Large Language Models to Improve Accuracy and Comprehensibility of Automated Code Review](https://dl.acm.org/doi/10.1145/3695993)**: Enhancing LLM accuracy and comprehensibility in automated code reviews.\n\n - **[Lessons from Building Static Analysis Tools at Google](https://cacm.acm.org/magazines/2018/4/226371-lessons-from-building-static-analysis-tools-at-google/fulltext)**: Why low false-positive rates are crucial (validating the need for specialized agents).\n\n\n## Security \u0026 Static Analysis AI\n\n_Tools focusing specifically on vulnerabilities and SAST (Static Application Security Testing)._\n\n- **[Snyk DeepCode](https://snyk.io/platform/deepcode-ai/)** - AI-powered engine to find security flaws faster than traditional static analysis.\n- **[Semgrep AI](https://semgrep.dev)** - Combines rule-based static analysis with AI to reduce false positives in security scanning.\n\n## CLI \u0026 Local Workflows\n\n_Command-line tools for local reviews and \"hacker\" workflows._\n\n- **[Aider](https://github.com/paul-gauthier/aider)** - AI pair programming in your terminal.\n- **[Mentat](https://github.com/biobootloader/mentat)** - Coordinate edits across multiple files using command line.\n- **[OpenCommit](https://github.com/di-sukharev/opencommit)** - Generates semantic git commit messages automatically.\n- **[prpack](https://github.com/Lucas2944/prpack)** - Zero-dependency Node CLI that packs a pull request (diff plus the full post-change content of every touched file) into a single markdown file optimized for LLM code review. Companion [GitHub Action](https://github.com/Lucas2944/prpack-action) and [browser demo](https://lucas2944.github.io/prpack-demo/) available.\n- **[LegacyDoc AI](https://www.romanticode.com/tools/ai-code-audit-report/)** - VS Code extension that generates AI code audit reports, architecture maps, and review-ready context packs from a workspace before cleanup or code review.\n- **[Signum](https://github.com/heurema/signum)** - Multi-model code review pipeline that dispatches diffs to Claude, Codex, and Gemini as independent reviewers with adversarial isolation, then bundles findings into a tamper-evident proofpack.\n- **[claude-code-multi-model-review](https://github.com/baiyanmo/claude-code-multi-model-review)** - Claude Code skill that invokes multiple AI models (DeepSeek, Doubao, Qwen, OpenAI) in parallel to review git diffs with cross-validation across model outputs.\n- **[Optibot CLI](https://getoptimal.ai)** - Review uncommitted changes, branch diffs, or patch files from the terminal for GitHub \u0026 GitLab. API-key auth and stable exit codes for CI/CD (GitHub Actions, GitLab CI, Jenkins), plus token-metered security scans.\n- **[h5i](https://github.com/h5i-dev/h5i)** - Rust CLI that runs several coding agents (Claude Code, Codex) on the same task in isolated git-worktree sandboxes, has them peer-review each other, then a neutral verifier replays each candidate, runs the tests itself, and merges the one that passes. Run metadata (prompts, models, commands, logs, verdict) is versioned in the repo under refs/h5i/*.\n\n\n## Benchmarks\n- **[Code Review Benchmark](https://codereviewbench.com/)**: Comprehensive evaluation of LLM performance in AI-powered code review tasks.\n- **[SWE-bench](https://www.swebench.com/)** - Evaluation framework for language models on real-world software engineering issues.\n- **[HumanEval](https://github.com/openai/human-eval)** - OpenAI's dataset for evaluating code generation capabilities.\n- **[ReviewBenchLite](https://www.polarity.so/research/2)** - Comprehensive evaluation of code review agents on top 100 git repos.\n- **[ShopPay Audit Benchmark](https://github.com/Dmatut7/shoppay-audit-benchmark)** - Spec-grounded benchmark for testing whether AI code review/coding agents catch business-logic defects in payment, wallet, webhook, and authorization flows.\n\n---\n\n## Contributing\n\nContributions are welcome! Please read the [contribution guidelines](CONTRIBUTING.md) first.\nIf you are a founder or maintainer of a tool listed here and want to update your description, feel free to open a PR.\n\n## License\n\n[![CC0](https://licensebuttons.net/p/zero/1.0/88x31.png)](https://creativecommons.org/publicdomain/zero/1.0/)\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/kodustech%2Fawesome-ai-code-review/projects"}