aicoolies logo

Open Code Review

Alibaba's open-source hybrid AI code reviewer with line-level comments

open sourceupdated Aug 1, 2026

Open-source (Apache-2.0) CLI code reviewer from Alibaba that pairs deterministic rule pipelines with an LLM agent to post precise, line-level review comments. Runs locally or in CI, is provider-agnostic across OpenAI/Anthropic-compatible endpoints, and ships built-in rules for common defects.

Open Code Review (ocr) is an Apache-2.0 CLI code-review tool open-sourced by Alibaba, built on a hybrid architecture that combines deterministic pipelines with an LLM agent. It reviews Git diffs or scans whole files and returns line-level comments, with independent positioning and reflection modules aimed at reducing false positives. Built-in fine-tuned rules target null-pointer exceptions, thread-safety issues, XSS, and SQL injection. The project states it originated from Alibaba's internal system and "served tens of thousands of developers and identified millions of code defects" (vendor claim, not independently verified). Integration surface: ready-made GitHub Actions, GitLab CI, and GitFlic CI pipelines; installable as a Claude Code / Codex / Cursor plugin or Agent Skill; and an MCP server. It is provider-agnostic — Anthropic, OpenAI, Dashscope, Deepseek, Z-AI, plus any OpenAI/Anthropic-compatible custom endpoint, so no model lock-in. Standard AI-reviewer data-flow caveat: diffs/files are sent to whichever LLM endpoint you configure. Telemetry is disabled by default (optional OTLP export); config lives locally in ~/.opencodereview/config.json.

Pricing

Free and open-source (Apache-2.0). No license/subscription cost; you pay only for the LLM API calls to your chosen provider.

Platforms

CLI on Windows/macOS/Linux (`ocr review`/`ocr scan`). CI/CD via GitHub Actions, GitLab CI, GitFlic CI. Coding-agent plugins for Claude Code, Codex, Cursor; Agent Skill; MCP server. Provider-agnostic.

Categories

Tags

Alternatives

CodeRabbit logo

CodeRabbit

AI-powered code review

AI-powered code review tool that automatically analyzes pull requests and provides line-by-line feedback on code quality, bugs, security vulnerabilities, and best practices. Integrates with GitHub and GitLab as a bot that comments on PRs. Uses LLMs to understand code context and suggest improvements. Learns from your codebase patterns and team preferences. Supports all major programming languages. Reduces review cycle time while catching issues human reviewers might miss.

freemium
Greptile logo

Greptile

AI code review with full codebase context

Greptile is a Y Combinator-backed AI code review tool that indexes your entire codebase to build a semantic code graph of functions, classes, and dependencies. Unlike diff-only reviewers, it catches cross-file issues, architectural drift, and convention violations with an 82% bug catch rate. Supports GitHub, GitLab, Jira, Slack, and VS Code. Offers cloud and self-hosted VPC deployment with SOC2 Type II compliance. Used by 250+ companies including Stripe and Amazon.

paid
Codacy logo

Codacy

Automated code quality

Codacy is a managed code quality, security and AI-guardrails platform for GitHub, GitLab and Bitbucket teams. It scans pull requests and repositories for quality, coverage and security issues while adding AI Inventory, AI Guardrails, AI Risk Hub, AI Reviewer and Verity beta surfaces for AI-assisted engineering.

freemium
SonarQube logo

SonarQube

Code quality and security analysis platform

SonarQube is an open-source code quality and security platform with 10K+ GitHub stars that inspects code for bugs, vulnerabilities, code smells, and security hotspots. It enforces quality gates in CI/CD pipelines, supports 30+ languages in Team plans and 40+ in Enterprise, and remains the industry standard for static code quality management.

Open Source

Related Tools

Brooks-Lint logo

Brooks-Lint

AI code review grounded in twelve classic software-engineering books

Open-source (MIT) AI reviewer with a distinctive angle: findings are grounded in twelve classic engineering books, cited by source, and framed as decay-risk diagnostics with a 0–100 Health Score. Runs as an Agent Skill across Claude Code, Gemini CLI, Codex, and other coding agents, with GitHub Actions quality gates and SARIF output.

Open Source
shippie

Shippie

Extensible open-source AI code review agent with emerging QA automation

Open-source (MIT) AI code-review agent formerly known as Code Review GPT. Its released workflow reviews pull requests in GitHub Actions or staged changes locally, supports remote MCP tools and project instruction files, and works with Anthropic, OpenAI, OpenRouter, and Cloudflare providers. The main branch also contains an unreleased autonomous QA workflow. Anonymous usage telemetry is enabled by default and can be disabled.

Open SourceTelemetry
roborev logo

roborev

Continuous local code-review loops for commits produced by AI coding agents

roborev is an MIT-licensed local review system that checks every commit in the background, stores findings in a review queue, and feeds actionable issues back into AI coding sessions. Git hooks, a TUI, branch and dirty-tree analysis, Codex and Claude agent hooks, plus iterative fix/refine commands turn review into a continuous agent workflow.

Open SourceTelemetry
Mergify logo

Mergify

Merge queue, CI insights, flaky-test controls, and stacked pull requests for GitHub teams

Mergify is a pull request automation platform that keeps main branches green with merge queue batching, merge protections, CI Insights, flaky-test detection, and stacked pull requests. Its Stacks workflow turns commits on one local branch into focused PR chains, helping teams review large AI-generated or feature-heavy changes without losing queue safety.

freemium
Baz logo

Baz

Telemetry-aware AI code reviewer that checks how pull requests may affect real services.

Baz is an AI code-review platform focused on production-aware pull requests. Instead of only reading the diff, Baz connects code changes to application telemetry so reviewers can understand what endpoints, services, and runtime behavior may be affected. That makes it a useful complement to existing AI PR bots when the question is not just whether a change looks correct, but whether it could break a live system.

freemiumTelemetry
reviewdog logo

reviewdog

Automated code review for any linter on CI

reviewdog is an open-source automated code review tool that integrates any linter or static analysis tool with GitHub, GitLab, Bitbucket, and Gitea pull requests. Parses output in errorformat, Checkstyle XML, SARIF, and JSON formats to post inline review comments on changed lines only. Works with GitHub Actions, Travis CI, CircleCI, GitLab CI, and Jenkins. Supports 40+ languages through universal linter adapter architecture.

Open Source