Nicheloom visits: 61,865 all-time · 8,336 in the last 7 days

The opportunity tracker for new startups.

Today: 1,033 launches · Niche of the day: ai video generation tools · See what launched today →

DevGhost

Measure developer output from Git, before and after AI

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

DevGhost estimates each developer's output from Git history and the content of code changes, not lines, commit counts or tracked hours. Every change is measured against one fixed benchmark: a mid-level developer who knows the project and works without AI. See who is above it, who is below, and whether output grew after AI coding tools arrived. Our own ML models, no LLMs. Cloud, fully Local (code and results never leave your machine) or On-Prem. Start free.

PH · launched Nov 16, 2026 · 1 upvote (top 65%) · 0 views

Niche: engineering and workflow analytics platforms · 40 launches, 4 in the last 7 days · Explore this niche →

Category and tags

  • Horizontal
  • Analytics & BI
  • B2B
  • Not AI
  • Commercial product
  • Productivity
  • Analytics
  • Developer Tools

Visit website ↗ Source listing ↗

Could you build this?

Partial The Git ingestion and dashboard are standard, and an LLM can score code changes against a benchmark prompt. Credible measurement of developer output, though, requires calibrated rubrics and validation against human judgment, which vibe coding alone won't supply.

What it would actually take: Build a Git analytics backend (GitHub/GitLab APIs or local repo parsing) that extracts per-change diffs and context, then sends them to an LLM with a fixed rubric for a 'mid-level developer without AI' baseline. The hard part is validity: the scoring needs calibration sets labeled by experienced engineers, bias and gaming controls, and ongoing evaluation. Expertise in engineering measurement, labor-law and HR sensitivities, and LLM evaluation is needed alongside the app work.

Competitors

Other products that read as similar to this one : 230 launches clear the similarity bar, closest 8 shown.

Attention rank: #122 of 231 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 371 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.