Browse by type
English | 简体中文 | 日本語 | 한국어 | Русский
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.

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).
Explore the AACR-Bench dataset on Hugging Face.
| Metric | What it measures | Why it matters |
|---|---|---|
| F1 | Harmonic mean of precision and recall | Best single number for overall review quality |
| Precision | Proportion of reported issues that are real defects | Higher = fewer false alarms to triage |
| Recall | Proportion of real defects that are found | Higher = fewer issues slip through review |
| Avg Time | Wall-clock time per review | Matters for CI pipeline latency |
| Avg Token | Total tokens consumed per review | Directly impacts API cost |

If you've used general-purpose agents like Claude Code with Skills for code review, you've likely encountered these pain points:
The root cause: a purely language-driven architecture lacks hard constraints on the review process.
Open Code Review's core philosophy is to combine deterministic engineering with an agent, each handling what it does best.
Deterministic Engineering — Hard Constraints
For review steps that must not go wrong, engineering logic — not the language model — guarantees correctness:
message_en.properties and message_zh.properties are bundled together). Each bundle runs as a sub-agent with isolated context — a divide-and-conquer strategy that stays stable on very large changesets and naturally supports concurrent review.Agent — Dynamic Decision-Making
The agent's strengths are concentrated where they matter most — dynamic decisions and dynamic context retrieval:
Use the skills in Claude Code, Codex, Cursor, Kimi Code, or another agent that supports Agent Skills and can run local commands. Both modes require Git >= 2.41 and the ocr CLI; only native mode requires an OCR model provider.
Run in the project you want to review, then select the skills you need and your agent in the installer:
npx skills add alibaba/open-code-review
The skills guide your agent to install ocr if it is missing, subject to your environment's permissions. You can also install it ahead of time with npm install -g @alibaba-group/open-code-review. Prefer a plugin or manual installation? See the agent-specific setup guide, or copy the desired folders from skills/ into your agent's skill directory.
| Native mode | Delegation mode | |
|---|---|---|
| Skill | open-code-review |
open-code-review-delegate |
| Who reviews? | OCR's specialized review agent and pipeline | Your current coding agent, following OCR's review pipeline and guardrails |
| Model and authentication | OCR's own provider configuration | Your host agent's existing model and authentication |
| Choose it when | You have a model endpoint for OCR and want its full review pipeline | You have no separate API key, or want to use your existing agent subscription/setup |
No separate key? Start with delegation mode. It skips OCR provider setup, not the host agent's own authentication, usage limits, or costs. A host-agent subscription is not automatically an API credential for native mode. In delegation mode, OCR's CLI and skill together provide the review pipeline and guardrails: file selection, rule resolution, coverage requirements, and structured reporting. The host agent performs analysis, positioning, and reporting within that workflow; it does not run OCR's full native pipeline.
For native mode, configure a provider once with ocr config provider and ocr config model. Authentication depends on the provider; see Configuration.
npm install -g @alibaba-group/open-code-review
After installation, the ocr command is available globally.
For other installation methods (install script, GitHub Release binary, from source), see Installation.
1. Configure LLM
You must configure an LLM before reviewing code, unless you use Delegation Mode.
ocr review, the /open-code-review:review command, and the open-code-review skill use OCR's own provider configuration, not your Claude Code Team/Pro subscription login. Authentication requirements depend on the provider; see Configuration./open-code-review:delegate-review command and the open-code-review-delegate skill use the host agent's configured model and authentication. No separate LLM configuration or credentials are needed in OCR. See the Claude Code install steps.ocr config provider # Select a built-in provider or add a custom one
ocr config model # Pick a model for the active provider

The interactive UI guides you through provider selection, API key entry, and model configuration, then automatically tests connectivity.
For CLI setup, environment variables, custom providers, and other advanced configuration, see Configuration.
2. Review
cd your-project
# Workspace mode — review all staged, unstaged, and untracked changes
ocr review
# Current branch — review changes since it diverged from main (--to defaults to HEAD)
ocr review --from main
# Branch range — reviews feature-branch's changes since it diverged from main (merge-base mode)
ocr review --from main --to feature-branch
# Single commit
ocr review --commit abc123
# Resume an interrupted range or commit review
ocr session list
ocr review --from main --to feature-branch --resume <session-id>
# Full-file scan — review whole files instead of a diff (no git history needed)
ocr scan # scan the entire repository
ocr scan --path internal/agent # scan a directory or specific files
ocr scan --resume <session-id> # resume an interrupted full-file scan
# Save results to a file (recommended for AI host agents)
ocr review --format json --output result.json
# Delegation mode — let your AI coding agent perform the review itself
# OCR handles file selection and rule resolution; no LLM configuration needed
ocr delegate preview
ocr delegate rule src/main.go src/handler.go
Full documentation lives at open-codereview.ai/docs:
browse all types & interfaces →
$ claude mcp add open-code-review \
-- python -m otcore.mcp_server <graph>