Hi HN! I'm sharing MergeMint, an open-source platform we built at TextCortex AI to automatically evaluate and score pull requests using Claude AI. The problem we had: Our engineering team lacked visibility into contribution impact, and performance reviews felt subjective. We wanted objective metrics without the overhead of manual PR reviews. How it works: When a PR merges, MergeMint analyzes the diff, linked issues, and commits using Claude AI. It classifies component/severity, calculates a score, posts feedback on the PR, and updates team leaderboards. The results after 6 months: • 3x increase in developer engagement with our internal bug bounty program • Team members actively compete on leaderboards (gamification really works!) • Performance reviews now backed by concrete contribution data • We caught and rewarded high-impact work that was flying under the radar The scoring is fully configurable – we defined our components (auth, API, UI) with multipliers and severity levels (P0-P3) with base points. Claude does the classification, we control the weights. Honestly, the gamification aspect surprised us the most. Developers started paying more attention to linking issues, writing better PR descriptions, and picking up high-priority work. Tech stack: Next.js 15, Supabase (PostgreSQL), Anthropic Claude, Tailwind v4. Fully self-hostable with Docker. We're open-sourcing it because it's been transformative for our team, and we think other engineering orgs could benefit. GitHub: https://github.com/MergeMint/mergemint-app Free SaaS version: https://mergemint.dev Happy to answer questions about our experience deploying this in production or the technical implementation! |