The open source AI code review agent.

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.

If you've used general-purpose agents like Claude Code with Skills for code review, you've likely encountered these pain points:

• Incomplete coverage — On larger changesets, agents tend to "cut corners," selectively reviewing only some files and missing others.
• Position drift — Reported issues frequently don't match the actual code location, with line numbers or file references drifting off target.
• Unstable quality — Natural-language-driven Skills are hard to debug, and review quality fluctuates significantly with minor prompt variations.

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:

• Precise file selection — Determines exactly which files need review and which should be filtered, ensuring no important change is missed.
• Smart file bundling — Groups related files into a single review unit (e.g., 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.
• Fine-grained rule matching — Matches review rules to each file's characteristics, keeping the model's attention sharply focused and eliminating information noise at the source. Compared to purely language-driven rule guidance, template-engine-based rule matching is more stable and predictable.
• External positioning and reflection modules — Independent comment-positioning and comment-reflection modules systematically improve both the location accuracy and content accuracy of AI feedback.

Agent — Dynamic Decision-Making

The agent's strengths are concentrated where they matter most — dynamic decisions and dynamic context retrieval:

• Scenario-tuned prompts — Prompt templates deeply optimized for code review, improving effectiveness while reducing token consumption.
• Scenario-tuned toolset — Distilled from deep analysis of tool-call traces in large-scale production data — including call frequency distributions, per-tool repetition rates, and the impact of new tools on the overall call chain — resulting in a purpose-built toolset that is more stable and predictable for code review than a generic agent toolkit.

Via NPM (Recommended)

npm install -g @alibaba-group/open-code-review

After installation, the ocr command is available globally.

From GitHub Release

Download the latest binary from GitHub Releases:

# macOS (Apple Silicon)
curl -Lo ocr https://github.com/alibaba/open-code-review/releases/latest/download/opencodereview-darwin-arm64
chmod +x ocr && sudo mv ocr /usr/local/bin/ocr

# macOS (Intel)
curl -Lo ocr https://github.com/alibaba/open-code-review/releases/latest/download/opencodereview-darwin-amd64
chmod +x ocr && sudo mv ocr /usr/local/bin/ocr

# Linux (x86_64)
curl -Lo ocr https://github.com/alibaba/open-code-review/releases/latest/download/opencodereview-linux-amd64
chmod +x ocr && sudo mv ocr /usr/local/bin/ocr

# Linux (ARM64)
curl -Lo ocr https://github.com/alibaba/open-code-review/releases/latest/download/opencodereview-linux-arm64
chmod +x ocr && sudo mv ocr /usr/local/bin/ocr

# Windows (x86_64) — move ocr.exe to a directory in your PATH
curl -Lo ocr.exe https://github.com/alibaba/open-code-review/releases/latest/download/opencodereview-windows-amd64.exe

# Windows (ARM64) — move ocr.exe to a directory in your PATH
curl -Lo ocr.exe https://github.com/alibaba/open-code-review/releases/latest/download/opencodereview-windows-arm64.exe

From Source

git clone https://github.com/alibaba/open-code-review.git
cd open-code-review
make build
sudo cp dist/opencodereview /usr/local/bin/ocr

1. Configure LLM

You must configure an LLM before reviewing code.

Option A: Interactive setup (Recommended)

ocr config provider          # Select a built-in provider or add a custom one
ocr config model             # Pick a model for the active provider

Option B: Manual config

ocr config set llm.url https://api.anthropic.com/v1/messages
ocr config set llm.auth_token your-api-key-here
ocr config set llm.model claude-opus-4-6
ocr config set llm.use_anthropic true

Config is stored in ~/.opencodereview/config.json.

auth_header (optional): Controls which HTTP header carries the API key when using Anthropic. Defaults to authorization (Bearer token) if omitted. If you use a standard sk-ant-* API key, you must set it to x-api-key:

ocr config set llm.auth_header x-api-key

Supported values: x-api-key, authorization (alias: bearer). Other values are rejected with an error.

Option C: Environment variables (highest priority)

export OCR_LLM_URL=https://api.anthropic.com/v1/messages
export OCR_LLM_TOKEN=your-api-key-here
export OCR_LLM_MODEL=claude-opus-4-6
export OCR_USE_ANTHROPIC=true

It is also compatible with Claude Code environment variables (ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, ANTHROPIC_MODEL) and parses ~/.zshrc / ~/.bashrc for those exports.

Note for CC-Switch Users: If you are using CC-Switch with routing service enabled, you can point llm.url to the CC-Switch proxy address without additional configuration:

• For Claude provider: set llm.url to http://127.0.0.1:15721
• For Codex provider: set llm.url to http://127.0.0.1:15721/v1
• Set llm.model according to your provider settings
• llm.auth_token can be any value
• extra_body settings still apply

2. Test Connectivity

ocr llm test

3. Review

cd your-project

# Workspace mode — review all staged, unstaged, and untracked changes
ocr review

# Branch range — compare two refs
ocr review --from main --to feature-branch

# Single commit
ocr review --commit abc123

OCR can be seamlessly integrated into AI coding agents as a slash command, enabling code review directly within your agent workflow.

Use npx to install the OCR skill into your project:

npx skills add alibaba/open-code-review --skill open-code-review

This installs the open-code-review skill from the skills registry, which teaches your coding agent how to invoke ocr for code review, classify issues by priority, and optionally apply fixes.

For Claude Code, install the command plugin through the following command in Claude Code:

/plugin marketplace add alibaba/open-code-review
/plugin install open-code-review@open-code-review

This registers the /open-code-review:review slash command, which runs OCR and automatically filters and fixes issues.

For local Codex, install the Open Code Review plugin from this repository:

codex plugin marketplace add alibaba/open-code-review
codex
/plugins

For a local checkout or fork:

codex plugin marketplace add .
codex
/plugins

Install and enable Open Code Review, then start a new Codex thread and invoke it explicitly:

@Open Code Review review my current changes
@Open Code Review review this branch against main
@Open Code Review review and fix high-confidence issues

This registers a Codex skill that runs the local OCR CLI:

ocr review --audience agent

This integration does not change OCR's internal LLM backend and does not require configuring an OpenAI Responses API endpoint for Codex. OCR itself still requires the ocr CLI to be installed and configured as described in the CLI setup section.

Korean guide: plugins/open-code-review/CODEX.ko-KR.md

For a quick setup without any package manager, simply copy the command file to use the /open-code-review slash command in Claude Code.

Project-level (shared with team via git):

mkdir -p .claude/commands
curl -o .claude/commands/open-code-review.md \
  https://raw.githubusercontent.com/alibaba/open-code-review/main/plugins/open-code-review/commands/review.md

User-level (personal global use across all projects):

mkdir -p ~/.claude/commands
curl -o ~/.claude/commands/open-code-review.md \
  https://raw.githubusercontent.com/alibaba/open-code-review/main/plugins/open-code-review/commands/review.md

Prerequisite: All integration methods require the ocr CLI to be installed and an LLM configured. See Install and Configure LLM above.

OCR can be integrated into CI/CD pipelines to automate code review on Merge Requests / Pull Requests.

The core command for CI integration:

ocr review \
  --from "origin/main" \
  --to "<commit_sha>" \
  --format json

The --from flag accepts a branch ref (e.g., origin/main) or commit SHA as the base, while --to accepts a commit SHA or branch ref as the head. In CI environments, using commit SHA for --to is recommended to correctly handle fork PRs/MRs where the source branch doesn't exist on the origin remote.

The --format json flag outputs machine-readable results suitable for parsing in CI scripts.

See the examples/ directory for integration examples:

• github_actions/ — GitHub Actions integration example
• gitlab_ci/ — GitLab CI integration example

# Interactive provider and model setup
ocr config provider
ocr config model
ocr llm providers

# Preview which files will be reviewed (no LLM calls)
ocr review --preview
ocr review -c abc123 -p

# Review workspace changes with default settings
ocr review

# Review branch diff with higher concurrency
ocr review --from main --to my-feature --concurrency 4

# Review a specific commit with verbose JSON output
ocr review --commit abc123 --format json --audience agent

# Provide requirement context for more targeted review
ocr review --background "Adding rate limiting to the login API"

# Use custom review rules
ocr review --rule /path/to/my-rules.json

# Preview which rule applies to a file
ocr rules check src/main/java/com/example/Foo.java
ocr rules check --rule custom.json src/main/resources/mapper/UserMapper.xml

# View review session history in browser
ocr viewer
ocr viewer --addr :3000

The viewer serves session JSONL contents (LLM request messages and responses) over HTTP. It enforces a Host-header allowlist on every request: loopback names (localhost, 127.0.0.0/8, ::1) and the concrete bind host are always allowed. Wildcard binds (--addr :3000, --addr 0.0.0.0:3000) and other non-loopback Hostnames must be added via the OCR_VIEWER_ALLOWED_HOSTS environment variable (comma-separated):

OCR_VIEWER_ALLOWED_HOSTS=review.internal,ocr.lan ocr viewer --addr :3000

This blocks DNS-rebinding attacks against the local viewer.

OCR resolves review rules using a four-layer priority chain. Each layer uses first-match-wins: if a file path matches a pattern, that rule is used; otherwise it falls through to the next layer.

Layers 1–3 share the same JSON format:

{
  "rules": [
    {
      "path": "force-api/**/*.java",
      "rule": "All new methods must validate required parameters for null values"
    },
    {
      "path": "**/*mapper*.xml",
      "rule": "Check SQL for injection risks, parameter errors, and missing closing tags"
    }
  ]
}

• path supports ** recursive matching and {java,kt} brace expansion.
• Within each layer, rules are evaluated in declaration order — the first match wins.
• If a rule file does not exist, it is silently skipped.

Rule files also support include and exclude fields to control which files enter the review scope:

{
  "rules": [
    {"path": "**/*.java", "rule": "Check for null safety"}
  ],
  "include": ["src/main/**/*.java", "lib/**/*.kt"],
  "exclude": ["**/generated/**", "vendor/**"]
}

Filter decision priority (highest to lowest):

How it works:

• include and exclude follow the same priority chain as review rules (--rule > project config > global config). The highest-priority layer that has include/exclude configured takes effect as a whole — patterns are not merged across layers.
• exclude always wins over include — a file matching both is excluded.
• include acts as a bypass for built-in default exclude patterns (e.g., test files), not as an exclusive allowlist — files not matching any include pattern still proceed through the default filter checks normally.
• Pattern syntax: supports ** recursive matching, * single-segment matching, and {a,b} brace expansion. Matching is case-insensitive.

Built-in default exclude patterns (filters test files, etc. — can be overridden with include):

**/*_test.go, **/*Test.java, **/*Tests.java, **/*_test.rs,
**/*.test.{js,jsx,ts,tsx}, **/*.spec.{js,jsx,ts,tsx}, **/__tests__/**,
**/src/test/java/**/*.java, **/src/test/**/*.kt,
**/test/**/*_test.py, **/tests/**/*_test.py, **/*_test.py,
**/*_spec.rb, **/spec/**/*_spec.rb, **/oh_modules/**

Config file: ~/.opencodereview/config.json

Environment variables take precedence over the config file.

OpenTelemetry integration for observability (spans, metrics). Disabled by default.

ocr config set telemetry.enabled true
ocr config set telemetry.exporter otlp
ocr config set telemetry.otlp_endpoint localhost:4317

Set telemetry.content_logging to include LLM prompts and responses in exported data.

See CONTRIBUTING.md for development setup, coding guidelines, and how to submit pull requests.

Apache-2.0 — Copyright 2026 Alibaba