Review economics
microsoft/VibeVoice
Read from the 41 most recently merged pull requests ·
Not enough merged pull requests on both sides yet to compare how they land in review.
≥5%
Attributed
a floor
2
Attributed PRs
39
Other PRs
41
Read
Attributed — the latest 2
The rest — the latest 5
#423 Update news section in README.md
0 reviews · 1h to merge
#422 Add VibeVoice-ASR-BitNet CPU inference release
0 reviews · 5h to merge
#313 docs: minor wording fixes in contributing and VibeVoice guides
0 reviews · 12.0d to merge
#280 fix: NameError when no speech output in realtime demo
0 reviews · 10.8d to merge
#270 Fix Spelling (and grammar)
0 reviews · 11.2d to merge
How this was measured
5% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work.
Detected: Claude Code, GitHub Copilot coding agent.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read microsoft/VibeVoice weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on microsoft/VibeVoice — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository