Repolode
Submit
alibaba

alibaba/open-code-review

AI-powered code review CLI that pairs deterministic file selection and rules with an LLM agent to leave line-level review comments on Git diffs.

Open-source alternative to:CodeRabbit

View on GitHubWebsite
Stars
49,564
Forks
3,637
Open issues
342
Last commit
yesterday

What is it?

Open Code Review is a command-line tool that reviews code changes with an LLM. It reads Git diffs, selects which files need review, groups related files into bundles, and sends each bundle to an agent that can read full file contents, search the codebase, and inspect other changed files for context. The output is structured review comments tied to specific lines.

The project splits work between fixed engineering logic and the model. File selection, rule matching, and comment positioning are handled by deterministic modules, while the agent handles dynamic decisions and context retrieval. The built-in ruleset covers issues such as null pointer dereferences, thread safety, XSS, and SQL injection across multiple languages.

Besides reviewing diffs for a workspace, a branch range, or a single commit, the `ocr scan` command reviews whole files or directories. It supports OpenAI- and Anthropic-compatible endpoints, and can run in a delegation mode where a coding agent such as Claude Code performs the review with its own model.

Key features

  • 01Reviews Git diffs for a workspace, a branch range, or a single commit.
  • 02Produces structured review comments with line-level positioning.
  • 03Includes built-in rules for NPE, thread-safety, XSS, and SQL injection issues.
  • 04Scans whole files or directories without requiring a diff via `ocr scan`.
  • 05Works with OpenAI- and Anthropic-compatible model endpoints.
  • 06Offers plugins for Claude Code, Codex, Cursor, Kimi Code, and OpenCode.

Use cases

  • Adding automated review of pull requests to a CI/CD pipeline such as GitHub Actions or GitLab CI.
  • Reviewing a feature branch against main before opening a merge request.
  • Auditing an unfamiliar codebase or directory that has no meaningful diff.
  • Letting an AI coding agent run the review with its own model through delegation mode.

Quick start

  1. 1

    Install the CLI globally via npm

    npm install -g @alibaba-group/open-code-review
  2. 2

    Configure an LLM provider

    ocr config provider
  3. 3

    Pick a model for the active provider

    ocr config model
  4. 4

    Run a review in your Git project

    ocr review

Things to know

  • Requires Git 2.41 or newer.
  • Reviews need a configured LLM endpoint and API key, unless you use Delegation Mode.
  • Recall is lower than general-purpose agents, a deliberate trade-off for precision.

In collections

AI code review toolsAI coding assistants & agentsAI agent skill librariesCLI & terminal toolsTesting frameworks & test automation tools

Topics

#code-review#ai#llm#agent#git#cli#static-analysis#ci-cd#agent-skills#code-review-assistant

FAQ

What is open-code-review?
AI-powered code review CLI that pairs deterministic file selection and rules with an LLM agent to leave line-level review comments on Git diffs. Open Code Review is a command-line tool that reviews code changes with an LLM. It reads Git diffs, selects which files need review, groups related files into bundles, and sends each bundle to an agent that can read full file contents, search the codebase, and inspect other changed files for context. The output is structured review comments tied to specific lines.
Is open-code-review free to use? What license does it have?
open-code-review is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is open-code-review still maintained?
Actively maintained. The last commit to open-code-review was on Nov 6, 2026.
What can I use open-code-review for?
Adding automated review of pull requests to a CI/CD pipeline such as GitHub Actions or GitLab CI. Reviewing a feature branch against main before opening a merge request. Auditing an unfamiliar codebase or directory that has no meaningful diff. Letting an AI coding agent run the review with its own model through delegation mode.
How do I install open-code-review?
Install the CLI globally via npm: npm install -g @alibaba-group/open-code-review Configure an LLM provider: ocr config provider Pick a model for the active provider: ocr config model Run a review in your Git project: ocr review
Where can I get open-code-review?
The source code and installation instructions are on GitHub: https://github.com/alibaba/open-code-review

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects