AI product Open source
Open Code Review is an open-source, AI-powered command-line code-review tool developed from Alibaba Group’s internal review assistant. It reads Git diffs and sends changed files to a configurable LLM through an agent with tool-use capabilities; the agent can read complete files, search the repository, and inspect other changed files for context before producing structured comments tied to source lines. Its hybrid architecture combines deterministic engineering with dynamic agent decisions: deterministic stages select and bundle files, match rules to file characteristics, and apply independent comment-positioning and reflection modules, while scenario-specific prompts and tools guide context retrieval and review. The `ocr scan` command audits complete files or directories without requiring a meaningful diff, and the project provides multilingual rules for issues including null-pointer exceptions, thread safety, cross-site scripting, and SQL injection. It supports configurable model endpoints, including OpenAI- and Anthropic-compatible endpoints, and requires Git 2.41 or newer.
6 uses taken from transcripts — each links to the moment in the video.
An open-source command-line AI code review agent for Git diffs. It analyzes full files and codebase context, then produces structured comments pinned to exact lines.
Provides hybrid AI code review with line-level precision. It combines deterministic engineering for file selection and comment positioning with an agent for context and judgment, aiming to produce accurate feedback with fewer tokens.
Reviews large code changes using deterministic file selection and rule matching together with a reasoning agent. It is designed to cover every changed file and place comments on the correct lines.
An open-source AI-powered code review CLI from Alibaba. It combines deterministic checks with an LLM agent that examines diffs and codebases, produces line-level comments, detects issues, and can apply fixes.
An open-source AI-powered code review CLI from Alibaba that pairs deterministic pipelines with an LLM agent. It reads your git diff, inspects full files and the codebase, returns line-level comments, catches issues like null pointer bugs, thread safety, XSS and SQL injection, and can auto-apply fixes. Works with OpenAI and Anthropic, with plugins for Claude Code and Codex.
An AI-powered code review CLI from Alibaba. It pairs deterministic pipelines with an LLM agent that reads git diffs, full files, and the codebase, returning line-level comments and auto-applying fixes; a multi-language rule set catches issues like null pointer bugs, thread safety, XSS and SQL injection. Works with OpenAI and Anthropic, with plugins for Claude Code and Codex.
6 in the library.