Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
alibaba/open-code-review
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.
- Stars
- 55,132
- +7 days
- —
- Forks
- 4,568
- Language
- Go
- License
- Apache-2.0
- Last push
- 22 Nov 2026
Summary
Summary written by AI from the README; it may be imprecise.This AI-powered code review CLI tool analyzes Git diffs and entire codebases to provide structured, line-level feedback. It combines deterministic file filtering and bundling with an LLM agent that searches the repository to understand context beyond surface-level changes. Developers can run reviews natively with a configured model endpoint or through delegation mode within agents like Claude Code.
Use it when
- Reviewing staged or branch-level Git diffs with line-level comments before opening a pull request
- Scanning an entire codebase or directory for defects without needing git diff history
- Running structured code reviews inside Claude Code using delegation mode and existing agent credentials
Install
npx skills add alibaba/open-code-reviewnpm install -g @alibaba-group/open-code-reviewCommands quoted from the repo's README. Read the README before running them.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.