By mrmans0n
Launch ai-review desktop app from AI agents to visually inspect git diffs for uncommitted changes, branches, or commits; request human code reviews via CLI; parse inline feedback JSON; apply fixes; and summarize changes before commit or merge.
npx claudepluginhub mrmans0n/ai-review --plugin ai-reviewOpen the ai-review desktop app to visually browse a diff. Use when the user wants to see changes in a visual diff viewer without a review feedback loop — just for viewing.
Request human code review via the ai-review desktop app. Use when code changes are complete and ready for a final human review before committing or merging. Opens an interactive diff viewer where the human can leave inline comments, then returns their feedback.
Open existing commits in the ai-review desktop app for review. Use when you need to review, understand, or get feedback on specific commits, a commit range, or a branch diff — not your own recent work, but existing history.
Present completed work to the human for optional review via the ai-review desktop app. Use when you've finished a task and want the human to see what you did — they can optionally leave feedback.
AI Review (air) is a desktop code review tool for reviewing diffs, adding inline comments, and generating structured prompts to send back to AI coding agents.
It brings a pull-request-style review experience to the human → AI feedback loop.
| Light | Dark |
|---|---|
![]() | ![]() |
air) — open AI Review from any Git repositoryCCtrl/⌘ + OAI Review ships with skills that AI coding agents can use to interact with the desktop app. The most important one is human-review, which lets the agent request your code review before committing — it runs air --wait, opens the diff viewer, blocks until you submit feedback, and the agent addresses each comment automatically.
| Skill | Description |
|---|---|
| human-review | Request human code review with inline comments and feedback loop |
| show-changes | Present completed work for optional review |
| review-commits | Open existing commits or branch diffs for review |
| browse-diff | Open the diff viewer just for browsing (no feedback loop) |
Install as a Claude Code plugin to give your agent access to all skills automatically:
claude plugin marketplace add https://github.com/mrmans0n/ai-review
claude plugin install ai-review
That's it — Claude Code will discover the skills and can invoke air during coding sessions.
Use the Skills tool to install:
npx skills add mrmans0n/ai-review
brew install --cask mrmans0n/tap/ai-review
This installs the app and the air CLI command.
Download the latest release from GitHub Releases:
.dmg (Apple Silicon).AppImage or .debmacOS note: The app is not code-signed with an Apple Developer certificate. When opening for the first time, macOS Gatekeeper may show an error saying the app is "damaged" or "can't be opened." To fix this, run:
xattr -cr /Applications/AI\ Review.appIf you installed via Homebrew, this is handled automatically.
pnpm install
pnpm electron:build
cd cli && ./install.sh
# then: air (from any git repo)
pnpm dev — run the web app onlypnpm electron:dev — run the desktop app with hot reloadCtrl/⌘ + O — file searchC — add commentCmd/Ctrl + Enter — submit commentEsc — close modals.
├── src/
│ ├── components/ # UI components (diffs, sidebar, comments, modals)
│ ├── hooks/ # React hooks for UI and state behavior
│ └── lib/ # Core client logic (git, prompt building, utilities)
├── electron/ # Electron main + preload (TypeScript)
├── core/ # Rust workspace (core-lib, core-sidecar, core-launcher)
└── cli/ # air launcher installer and CLI wiring
MIT — see LICENSE.
Terminal-based code review companion for Claude Code. Review diffs, leave structured feedback, and submit reviews — all from a TUI running alongside Claude.
AI-powered code review analysis — Run three-level AI analysis and implement-review-fix loops directly in your coding agent. Works standalone, no server required.
Native diff review window (Monaco + Glimpse) for AI coding agents. Browse changes since the merge-base with your base branch (or last commit / uncommitted), leave inline + file-level + overall comments on the slop, and have the agent address each item.
Close the feedback loop on AI coding: review plans and code changes with GitHub-style inline comments, then let the agent address them.
Codex, Gemini, Claude の3つの AI に並列でコードレビューを依頼し、統合レポートを生成する
Share bugs, ideas, or general feedback.
Code review plugin with a standalone reviewer agent and two skill strategies: disposable subagents for one-shot reviews and persistent team members for iterative reviews
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim