Hi HN,
I've been building and maintaining repos for a couple years, and one recurring frustration is tech debt piling up—garbage code, flaky tests, outdated deps—making it hard to get buy-in from PMs for cleanup time.
Inspired by discussions here on HN about developer productivity and tooling gaps, I built a small open-source MVP: Cosmic AI.
What it does:
Connects to your GitHub repo (OAuth, read-only).
Scans for issues and generates a heatmap (red = urgent, yellow = watch, green = healthy).
Quantifies debt in dollars/ROI (e.g., potential $67k/qtr saved), with a basic calculator for team size/salary.
It's fully open source free to use, and no sign-up for basic scans (waitlist for advanced reports).
I'm a solo tech guy iterating on this—would love feedback from the HN community:
Does the dollar/ROI framing feel useful for convincing non-tech stakeholders, or is hours/grading scale better?
What metrics/integration would make this more valuable (e.g., SonarQube ties, flaky test detection)?
Site/try it: cosmic-ai.pages.dev
Thanks! If it feels off or simplistic, be brutally honest—I'll use the feedback to improve (or pivot if needed)."
Connects to your GitHub repo (OAuth, read-only). Scans for issues and generates a heatmap (red = urgent, yellow = watch, green = healthy). Quantifies debt in dollars/ROI (e.g., potential $67k/qtr saved), with a basic calculator for team size/salary.
It's fully open source free to use, and no sign-up for basic scans (waitlist for advanced reports). I'm a solo tech guy iterating on this—would love feedback from the HN community:
Does the dollar/ROI framing feel useful for convincing non-tech stakeholders, or is hours/grading scale better? What metrics/integration would make this more valuable (e.g., SonarQube ties, flaky test detection)?
Site/try it: cosmic-ai.pages.dev Thanks! If it feels off or simplistic, be brutally honest—I'll use the feedback to improve (or pivot if needed)."