LaReview is a developer-first, local-first code review workbench designed to transform complex pull requests or diffs into structured, high-signal review workflows powered by AI assistance. Instead of overwhelming developers with raw diffs or automated comment spam, the tool analyzes code changes and generates an intent-driven review plan that groups changes into logical flows such as authentication, API behavior, or data handling, and prioritizes them based on risk. It operates as a desktop application with CLI integration, allowing users to launch reviews directly from their terminal while keeping all processing local to ensure security and prevent data leakage. The system presents reviews as hierarchical task trees, enabling developers to work through changes step by step, attach notes, and track progress across different review concerns.
Features
- AI-generated structured review plans grouped by flow and risk
- Hierarchical task tree for navigating and tracking review progress
- Local-first architecture with zero data leakage outside the machine
- Integration with existing AI coding agents for contextual analysis
- Visual tools like file heatmaps and architecture diagrams
- CLI and GUI workflow integration for seamless developer usage