alibaba/open-code-review

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A CLI code review tool that reads Git diffs and sends changed files to an LLM agent that can read files and search the codebase. It combines deterministic pipelines with the agent and writes line-level review comments.

How it helps ATF

Its mix of deterministic pipelines and an LLM agent is worth comparing for how Harness could check code results from executors such as Claude Code or Codex. Its choice of precision over recall could also be a reference.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

• XiaomiMiMo/MiMo-Code
  A terminal-native AI coding assistant that reads and writes code, runs commands and manages Git. It keeps a persistent memory of the project across sessions and also serves as the core engine of the MiMo Desktop app.
• BigPizzaV3/CodexPlusPlus
  An external launcher and manager for the OpenAI Codex and ChatGPT desktop app. Through the Chromium DevTools Protocol and a local helper service, it adds provider switching, protocol conversion, session management and interface tweaks without patching the official app.
• Kilo-Org/kilocode
  An open source AI coding agent for VS Code, JetBrains IDEs and the command line, where users choose among many models and switch between them mid-task. It also offers a web-based cloud agent and automated pull request reviews.
• esengine/DeepSeek-Reasonix
  A coding agent built around DeepSeek that runs as a single Go binary and can be used from a terminal, desktop app, browser or editor. It offers plan mode, permissions, a workspace sandbox, per-turn checkpoints and cache-aware context maintenance.
• DeusData/codebase-memory-mcp
  codebase-memory-mcp is an MCP server that parses code with tree-sitter and indexes a repository into a persistent knowledge graph of functions, classes, call chains, HTTP routes and cross-service links. It ships as a native executable for AI coding agents.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.