A desktop app for Git branches and GitHub pull requests. Comment on any line, publish when you're ready, and add an AI reviewer with your own model, or none. Free and open source.
I'm a developer and team lead. Since AI started writing so much of our code, reviewing it all has become the hardest part of my job. So I built Review: a desktop app for reviewing pull requests, where you can set up a team of AI reviewers from different providers to take the first pass. You still decide what gets published.
What it does: - Opens your local Git branches and GitHub pull requests in one window. ⌘P jumps to any of them. - Pins each review to exact commits, so the diff doesn't shift when someone pushes. - Keeps your comments on your machine until you publish them to GitHub as a review. - Adds an AI reviewer if you want one: OpenAI, Anthropic, Gemini, OpenRouter, or a local model in Ollama or LM Studio. Your keys are stored in the system keychain.
What's different about the AI part: it checks every change against a fixed set of rules (bugs, security, error handling, tests and more), and it shows which rules it actually checked, not just what it found. If a request fails, you can retry only the rules it missed. It can also call your MCP servers for context the code doesn't have, like the ticket behind a change.
It's free, open source (MIT) and needs no account. It runs on macOS, Windows and Linux.
One heads-up: the installers aren't signed yet, so your system will ask once the first time you open it. The website has the two-click fix.
I'd love to know: what's the most annoying part of code review for you today? And which model would you plug in first?
About Review on Product Hunt
“Code review on your own machine, with optional AI”
Review launched on Product Hunt on October 6th, 2026 and earned 70 upvotes and 1 comments, placing #34 on the daily leaderboard. A desktop app for Git branches and GitHub pull requests. Comment on any line, publish when you're ready, and add an AI reviewer with your own model, or none. Free and open source.
On the analytics side, Review competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Review performed against the three products that launched closest to it on the same day.
Who hunted Review?
Review was hunted by Hamed Qaderi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Review including community comment highlights and product details, visit the product overview.
Hamed Qaderi
Hi Product Hunt! I'm Hamed, and I made Review.
I'm a developer and team lead. Since AI started writing so much of our code, reviewing it all has become the hardest part of my job. So I built Review: a desktop app for reviewing pull requests, where you can set up a team of AI reviewers from different providers to take the first pass. You still decide what gets published.
What it does:
- Opens your local Git branches and GitHub pull requests in one window. ⌘P jumps to any of them.
- Pins each review to exact commits, so the diff doesn't shift when someone pushes.
- Keeps your comments on your machine until you publish them to GitHub as a review.
- Adds an AI reviewer if you want one: OpenAI, Anthropic, Gemini, OpenRouter, or a local model in Ollama or LM Studio. Your keys are stored in the system keychain.
What's different about the AI part: it checks every change against a fixed set of rules (bugs, security, error handling, tests and more), and it shows which rules it actually checked, not just what it found. If a request fails, you can retry only the rules it missed. It can also call your MCP servers for context the code doesn't have, like the ticket behind a change.
It's free, open source (MIT) and needs no account. It runs on macOS, Windows and Linux.
One heads-up: the installers aren't signed yet, so your system will ask once the first time you open it. The website has the two-click fix.
I'd love to know: what's the most annoying part of code review for you today? And which model would you plug in first?