Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Open-source AI coding assistant for VS Code. Code completion, chat, edits and reviews with local or hosted models. Your models, your infrastructure.
OrcaCode Review — the open code review harness. Multi-model reviews, merge gates, and no markup. Pay only for inference.
GitHub Actions bot that automatically reviews pull requests using the Claude API, posting inline comments and a summary on every PR.
Self-Hosted LLM Code Review Agent for GitLab, Forgejo and GitHub. Local LLM support
Rules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions before code, a reviewer that didn't write it, proof before done, bugs fixed as a class.
Evidence-based code review skills for Codex and Claude Code
20-pass adversarial audit for vibe-coded software. Injection, IDOR, races, N+1, idempotency, transactions, memory leaks — then a false-positive verifier.
CLI and a Chrome Extension designed for you to review AI generated code locally and on GitHub PRs
Ask your AI questions about its own code changes — from a Git diff viewer.
Fixes the AI reviewer findings on your PR, including the sibling instances the bot missed. Runs your tests before it pushes. Hard capped at 3 rounds. Claude Code and Codex.
A trajectory-evaluation-driven agentic code review pipeline that turns code changes into evidence-backed Findings.
Structured state for agent skills
Adversarial multi-agent code review — a committee of specialist reviewers that catches what single-pass AI review misses.
Run independent Claude Code, Codex, and Gemini code reviews in parallel and write one handoff for your coding agent.
🤖 AI PR Review Assistant：输入 GitHub PR 链接，结合仓库语义地图、动态上下文检索与质量门控，自动生成低噪音、可执行的代码审查建议。
LLM-powered code and CI/CD review agent for pull requests, with portable review skills and GitHub/GitLab/Jenkins reporting.
Spec-driven multi-agent Codex skill pack with /agent-do commands for planning, execution, reviews, security, design gates, and cross-platform coordination.
Open-source terminal pair-programming assistant — explains tracebacks, reviews code, drafts READMEs, and generates tests via any OpenAI-compatible LLM API (Groq by default). No heavy install, free API key, running in under 2 minutes. MIT licensed.
Evidence-based auditor for third-party software projects: code-only review, docs-vs-code validation, readiness assessment, risk classification, and actionable Markdown reports.
To associate your repository with the code-review-assistant topic, visit your repo's landing page and select "manage topics."