Open Code Review
Battle-tested AI code review agent with deterministic pipelines + LLM, fine-tuned security rules, and line-level comments.
Open source alternative to:
Open Code Review is an open-source AI code review agent built and battle-tested at Alibaba scale. It uses a hybrid architecture combining deterministic pipelines with an LLM Agent to deliver precise, line-level code review comments.
The tool includes a built-in fine-tuned ruleset covering common issues like NPE (Null Pointer Exceptions), thread-safety, XSS, and SQL injection. It is compatible with OpenAI and Anthropic models and can be self-hosted or integrated into CI/CD pipelines.
Unlike proprietary alternatives like GitHub Copilot or CodeRabbit, Open Code Review gives you full transparency and control over the review logic, rules, and model configuration.
Looking for contributors
This project is actively seeking help, join the community!
Repository details
Updated 7/20/2026, 5:00:41 AM
View RepositoryRepository activity
Compare Open Code Review with
Similar open source alternatives
Juggler
A self-hostable, GUI-first AI coding agent with editable conversation trees, plugin-based tools, and multi-client sessions.
Cursor
MiMoCode
An open-source terminal-native AI coding agent with cross-session memory, multiple agents, and support for any LLM provider.
Claude Code