Open Code Review is an open-source code review orchestration tool and agent plugin suite developed by Alibaba. Built primarily in Go with multi-interface distribution, it enables automated, context-aware code analysis across Git repositories, pull requests, and local development workspaces. In day-to-day workflows, Open Code Review operates as a standalone CLI utility, an npm-distributed tool, or as a plugin integration for IDEs (such as VS Code) and terminal agent environments like Claude Code. It inspects unified diffs and repository context to evaluate code quality, security posture, and logical consistency, generating structured review feedback and inline remediation suggestions. Unlike general-purpose coding agents focused on authoring code, Open Code Review acts as a specialized orchestrator for code validation and peer review workflows. Its architecture leverages modular agent skills and plugin definitions to enforce consistent review standards directly inside terminal sessions, CI workflows, and developer tooling. The project is fully open source under the Alibaba organization on GitHub, making it free to self-host and customize for internal engineering pipelines.
Specialized Review Orchestration — Focuses specifically on inspecting diffs, pull requests, and local changes for bugs, logic errors, and security vulnerabilities. - Claude Code & Agent Plugins — Includes pre-configured plugins and slash commands tailored for terminal agent harnesses like Claude Code. - CLI & Binary Distribution — Implemented in Go with pre-compiled binaries and npm package packaging for rapid deployment in local environments and CI pipelines. - VS Code Extension — Provides native editor integration to inspect review comments and recommendations directly within the IDE. - Modular Skill System — Supports extensible skill sets to adapt automated review rules to specific project architectures and language ecosystems.
Use cases
Use Case: Pre-Commit Local Code Reviews Developers run the CLI or VS Code extension on staged diffs before committing to catch formatting oversights, unhandled edge cases, and security vulnerabilities prior to pushing to remote repositories.
Use Case: CI/CD Pull Request Quality Gates Engineering teams integrate the review runner into automated CI pipelines to execute automated initial review passes on incoming pull requests, reducing manual review overhead for maintainers.
Use Case: Claude Code Review Extensions Developers using Claude Code can install the Open Code Review plugin commands to trigger specialized multi-step code evaluations from directly within interactive terminal agent sessions.
Who it is for
Open Code Review is built for development teams and individual engineers who want automated, agent-driven review workflows integrated into their Git processes, terminals, and IDEs. It is not intended as an autonomous code generator for building new features from scratch.
Install guide
Installation Install the package via npm or compile the Go binary directly from source: bash # Via npm npm install -g @alibaba/open-code-review # Or build from Go source go install github.com/alibaba/open-code-review/cmd/opencodereview@latest
First Run Ensure your LLM provider credentials (such as an API key and base URL) are configured in your environment or within the configuration file under .opencodereview/config.json: bash export OPENAI_API_KEY="your-api-key" # Optional: Set custom endpoint if routing through a gateway export OPENAI_BASE_URL="https://api.openai.com/v1"
Example Session Run a code review against your current git diff: bash # Review uncommitted changes in the current directory opencodereview review # Review a specific branch or commit diff opencodereview review --diff main..feature-branch
Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…
OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
Subtask — Subtask is an open-source CLI agent harness and orchestration tool developed by zippoxer in Go. It is built to coordinate…
EchoCoding — EchoCoding is an open-source agent harness and audio-augmented developer tooling layer created by launsion-boop. Designed to run alongside AI coding…
pi-reflect — pi-reflect is an open-source agent harness and self-improvement extension for pi coding agents, developed by jo-inc. It inspects agent session…