Verified project record
alibaba/open-code-review
alibaba/open-code-review provides structured, line-level AI code reviews by combining deterministic file selection and rule resolution with a configurable LLM agent. It addresses gaps in general-purpose code-review agents that can miss files or report issues at incorrect locations.
Project overview
It pairs deterministic pipelines with an LLM agent to produce line-level review comments, addressing accuracy issues reported in general-purpose agents.
- Project type
- AI Agent · AI Coding
- Use cases
- Coding & Development
- Deployment
- Refer to project documentation
- License
- Apache-2.0
Best for
- Developers and teams seeking structured, line-level AI code reviews through a CLI that combines deterministic pipelines with an LLM agent.
Key capabilities
- Reads Git diffs and changed files, then reviews them through a configurable LLM agent.
- Produces structured code-review comments with line-level precision.
- Allows the review agent to read full files, search the codebase, and inspect other changed files for context.
- Reviews entire repositories, directories, or specific files without requiring Git history.
- Provides deterministic file selection, rule resolution, file bundling, and rule matching for reviews.
- Lets a coding agent run the review with its own LLM without an OCR API key.
Limitations and risks
- The benchmark documentation says recall is lower than general-purpose agents as a deliberate precision-over-noise trade-off.
- A configurable LLM is required before ordinary reviews unless Delegation Mode is used.
- GPU requirements, minimum hardware, database requirements, data boundary, cost dependency, coding requirements, and telemetry are not documented.
Getting started
- Setup difficulty is medium. Installation is a global npm command, but the user must configure an LLM provider, API key, and model before ordinary reviews.
- Run `npm install -g @alibaba-group/open-code-review`, run `ocr config provider` to select or add a provider, run `ocr config model` to select a model, and run `ocr review` from the project directory.
Alternatives and comparisons
- Provides an agentic skills framework and software development methodology that enforces test-driven development and subagent-driven development for coding agents.
- Small, composable, and adaptable engineering skills for AI coding agents that enforce software engineering fundamentals like test-driven development, domain modeling, and code review.
- A complete system providing skills, instincts, memory optimization, continuous learning, security scanning, and research-first development across multiple AI agent harnesses.
Project comparisons
Evidence and sources
- GitHub project description: Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned…
- README: - **Incomplete coverage** — On larger changesets, agents tend to "cut corners," selectively reviewing only some files and missing others. - **Position drift** — Reported issues fr…
- README: 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.
- README: 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 cod…
- README: 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.
AI Search
Find projects, verify facts, compare options, or turn a complex need into an actionable plan
Try a searchA click only fills the search box; you stay in control
Project Details
0