engineering / agent
Open Code Review
A command-line tool for AI-assisted code review of Git diffs using a configurable language model.
At a glance
- Purpose
- A command-line tool for AI-assisted code review of Git diffs using a configurable language model.
- Runs in
- Local agent with shell, Web service
- Operating systems
- macOS, Linux, Windows
- Needs
- Runtime: Git 2.41+; Needs internet: Not stated; Needs accounts or API keys beyond your agent: Not stated
- Files and data
- Reads files: Yes; Writes files: Yes; Sends data to other services: Not stated
- Tool type
- Agent
- Delivery
- From GitHub
- Version
- Latest on the main branch
- Access
- Code on GitHub
- Compatibility
- According to the README, it supports Windows, macOS and Linux. It lists coding agent integrations for Claude Code, Codex, Cursor, Kimi Code, OpenCode and QCA Forward, and a portable skill for skill-compatible agents. The README's documentation list names GitHub Actions, GitLab CI, GitFlic CI and Gerrit for CI use. The GitHub description says the tool is OpenAI and Anthropic compatible.
- External costs
- The README says you configure a model provider, including an API key, before reviewing code. It says delegation mode uses your coding agent's own model and needs no OCR API key. The README does not name a model provider or a price. The repository is Apache-2.0-licensed and states no pricing. Your coding agent or model provider may charge for usage.
- Permissions
- The README's npm install command installs ocr globally. The README says model setup includes provider selection, API key entry and model configuration; delegation mode needs no OCR API key. The README says the agent reads changed files and repository context, uses Git for repository operations, can save results to a file and can be extended with external tools through an MCP server. The README also mentions an install script without giving its command. The top-level entries include scripts/ and extensions/; the README does not describe the behaviour of those folders.
- Usage terms
- Apache License 2.0, as stated in the repository. See its LICENSE file for the exact terms.
Code on GitHub
alibaba/open-code-review
Apache-2.0Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Topics: agent agent-skills code-review code-review-assistant harness repository-level-context
Public GitHub data fetched · 0 days old
Skill folders in this repository (4)
Folders that contain a SKILL.md file, from GitHub's file list on .
What it does
The README describes Open Code Review as an AI-powered code review command-line tool.The README says it reads Git diffs, sends changed files to a configurable language model and generates structured, line-level review comments. The README says its agent can read full files, search the codebase and inspect other changed files for context. The README also describes ocr scan for reviewing entire files without a meaningful diff.
The README describes engineering logic for file selection, bundling related files into review units and matching rules to files. The README describes the agent's role as dynamic decision-making and context retrieval. The README also lists coding-agent integrations and delegation mode, in which a coding agent uses its own model.
Who it is for
Developers who want AI-generated review comments on Git changes from the command line, from a coding agent or in a CI pipeline.Example tasks
Run ocr review to review staged, unstaged and untracked changes.Run ocr review --from main --to feature-branch to review a branch since it diverged from main.
Run ocr review --commit abc123 to review a single commit.
Run ocr scan --path internal/agent to review a directory or specific files without a diff.
Use delegation mode, with commands such as ocr delegate preview, so your coding agent performs the review itself.