open-code-review

Alibaba's battle-tested AI code-review CLI: deterministic pipelines + LLM agent, line-level comments, tuned rulesets (NPE, XSS, SQLi) — higher precision than general agents at ~1/9 the tokens.

10,947 755 Go Apache-2.0updated today

coding

View on GitHubDispute this mapping →

Curator's take

Two years as Alibaba's internal review assistant before open-sourcing, and it shows: the hybrid architecture (deterministic checks + tool-using LLM agent) is tuned for precision over recall — fewer, better line-level comments instead of noise — and their 200-PR benchmark honestly reports the trade-off, including losing to general agents on recall. `ocr scan` reviews whole files, useful for auditing unfamiliar code with no diff. Bring your own endpoint (OpenAI/Anthropic-compatible). NOT a replacement for your coding agent's judgment on architecture — it's a defect-finder (NPE, thread-safety, XSS, SQLi rulesets), strongest on the bug classes it was fine-tuned for; the deliberate low-recall bias means a clean review is not a clean PR.

Mapped by ShipWithAI editors · links verified

README.md

OpenCodeReview

English | 简体中文 | 日本語 | 한국어 | Русский

What is Open Code Review?

Open Code Review is an AI-powered code review CLI tool. It 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, we incubated it into an open source project for the community. Simply configure a model endpoint to get started.

It reads Git diffs, sends changed files to a configurable LLM via an agent with tool-use capabilities, and generates structured review comments with line-level precision. The agent can read full file contents, search the codebase, inspect other changed files for context, and produce deep reviews — not just surface-level diff feedback. Beyond diff review, ocr scan reviews entire files for auditing unfamiliar codebases or directories that have no meaningful diff.

Visit the official website for more details.

Highlights

Benchmark

Compared to general-purpose agents (Claude Code), Open Code Review achieves significantly higher Precision and F1 with the same underlying model, while consuming only ~1/9 of the tokens and completing reviews faster. Note that its Recall is lower than general-purpose agents — a deliberate trade-off favoring precision over noise.

A real-world code review benchmark built from 50 popular open-source repositories, 200 real Pull Requests, and 10 programming languages — cross-validated by 80+ senior engineers (1,505 annotated ground-truth issues).

| Metric | What it measures | Why it mat

Continue your stack

What teams reach for next — and why each earns a place beside open-code-review. Ranked by curator confidence.

Alternative to See all + compare →

pullfrog

Open-source, model-agnostic GitHub bot: tag @pullfrog on any issue or PR and your own coding agent (BYOK) runs the task inside GitHub Actions, context via an internal MCP server.

Why it fitsBoth put an AI agent on your GitHub PRs. pullfrog is the generalist — @mention it and your own agent runs any task in Actions; Open Code Review is the specialist — reviews only, hybrid deterministic+LLM, precision-tuned line comments.