HexmosTech/git-lrc

Free, Micro AI Code Reviews That Run on Git Commit

What it solves

git-lrc prevents software outages, security breaches, and technical debt by catching errors before they are committed to git history. It specifically addresses the problem of AI-generated code, which can silently introduce bugs, remove critical logic, or leak credentials without the developer noticing until the code reaches production.

How it works

The tool hooks into the git commit process to automatically trigger an AI-powered review of the diff. It uses a web-based UI to present a GitHub-style diff with inline AI comments categorized by severity (Critical, Warning, Info). Developers can then iterate by fixing the flagged issues and re-reviewing, or they can "vouch" for the code to take personal responsibility and commit.

Who it’s for

Software engineers and teams who use AI agents to generate code and want a universal, editor-independent safety net to ensure code quality and security across all repositories.

Highlights

  • Commit-time enforcement: Runs automatically on git commit or manually via git lrc review.
  • Risk-based triage: An Issue Navigator allows filtering by 10 risk categories and 100+ failure patterns.
  • Repository-specific rules: Users can define custom team preferences and constraints in a .lrc/ directory to guide the AI reviewer.
  • Git log tracking: Appends review status (iterations and coverage percentage) directly to the git commit message for institutional memory.
  • Summary Deck: Automatically generates a short slide deck summarizing changes and risks for quick orientation.
  • BYOK Support: Compatible with Gemini, OpenAI, Claude, DeepSeek, and OpenRouter.