alibaba/open-code-review: Trending on GitHub

Unlocking the Power of AI-Driven Code Review with Alibaba's Open Code Review

In the world of software development, code review is a crucial step in ensuring the quality and reliability of codebases. With the increasing complexity of modern software systems, manual code review can be a time-consuming and labor-intensive process. This is where AI-driven code review tools come in, promising to revolutionize the way we review and improve code. In this article, we'll delve into Alibaba's Open Code Review, a cutting-edge AI-powered code review tool that's gaining traction in the developer community.

What is Open Code Review?

Open Code Review is an AI-powered code review CLI tool that originated as Alibaba Group's internal official AI code review assistant. Over the past two years, it has served tens of thousands of developers and identified millions of code defects. After thorough validation at massive scale, the team incubated it into an open-source project for the community. With its ability to read Git diffs, send changed files to a configurable LLM (Large Language Model) via an agent with tool-use capabilities, and generate structured review comments with line-level precision, Open Code Review is poised to transform the way developers review and improve code.

Why Open Code Review?

The Problem with General-Purpose Agents

If you've used general-purpose agents like Claude Code with Skills for code review, you've likely encountered pain points such as incomplete coverage, position drift, and unstable quality. These issues arise from a purely language-driven architecture that lacks hard constraints on the review process. Open Code Review addresses these limitations by combining deterministic engineering with an agent, each handling what it does best.

Core Design: Deterministic Engineering × Agent Hybrid

Open Code Review's core philosophy is to combine deterministic engineering with an agent, each handling what it does best. Deterministic engineering ensures correctness in review steps that must not go wrong, while the agent handles dynamic decisions and context retrieval. This hybrid approach enables Open Code Review to provide more accurate and reliable code review results.

How to Use

To get started with Open Code Review, you'll need to install the CLI tool and configure an LLM. The installation process is straightforward, and you can choose from various options, including installing via NPM, downloading from GitHub Releases, or building from source. Once installed, you can configure an LLM by setting the llm.url, llm.auth_token, and llm.model configuration values.

Integrate with Coding Agents

Open Code Review can be seamlessly integrated into AI coding agents as a slash command, enabling code review directly within your agent workflow. You can install Open Code Review as a Skill using npx skills add alibaba/open-code-review --skill open-code-review, or install it as a Claude Code plugin using /plugin marketplace add alibaba/open-code-review and /plugin install open-code-review@open-code-review.

CI/CD Integration

Open Code Review can be integrated into CI/CD pipelines to automate code review on Merge Requests / Pull Requests. The core command for CI integration is ocr review --from "origin/main" --to "origin/feature-branch" --format json, which outputs machine-readable results suitable for parsing in CI scripts.

Commands

Open Code Review provides a range of commands to help you manage your code review workflow. Some of the key commands include:

• ocr review: Start a code review
• ocr rules check <file>: Preview which review rule applies to a file path
• ocr config set <key> <value>: Set configuration values
• ocr llm test: Test LLM connectivity
• ocr viewer: Launch WebUI session viewer on localhost:5483
• ocr version: Show version info

Review Rules

Open Code Review resolves review rules using a four-layer priority chain. Each layer uses first-match-wins, and you can customize review rules by setting the --rule flag or by using a custom JSON review rules file.

Configuration Reference

Open Code Review provides a range of configuration options to help you customize your code review workflow. Some of the key configuration options include:

• llm.url: LLM API endpoint URL
• llm.auth_token: API key / auth token
• llm.model: Model name
• language: Language (default: Chinese)
• telemetry.enabled: Enable or disable telemetry
• telemetry.exporter: Telemetry exporter (default: console)
• telemetry.otlp_endpoint: OTLP collector address

Telemetry

Open Code Review provides telemetry integration for observability (spans, metrics). You can enable or disable telemetry using the telemetry.enabled configuration option, and you can set the telemetry exporter using the telemetry.exporter configuration option.

Conclusion

Open Code Review is a cutting-edge AI-powered code review tool that's gaining traction in the developer community. With its ability to read Git diffs, send changed files to a configurable LLM via an agent with tool-use capabilities, and generate structured review comments with line-level precision, Open Code Review is poised to transform the way developers review and improve code. Whether you're a developer, a team lead, or a DevOps engineer, Open Code Review is definitely worth checking out.

Source: https://github.com/alibaba/open-code-review