Review economics
LykosAI/StabilityMatrix
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.4× the reviews submitted of the rest.
≥2%
Attributed
a floor
5
Attributed PRs
95
Other PRs
100
Read
Attributed — the latest 5
#1677 feat: in-app documentation viewer
2 reviews · 20.4d to merge
#1687 docs: add root index.html fallback so SWA deploy validation passes
2 reviews · 0h to merge
#1676 docs: VitePress docs site + Azure SWA deploy workflow
4 reviews · 8.4d to merge
#1665 v2.16.1
2 reviews · 1h to merge
#1591 Add self-healing settings file with corruption recovery
1 round · 8 reviews · 32h to merge
The rest — the latest 5
#1701 Add sign-windows option to release workflow
1 reviews · 2h to merge
#1700 v2.16.2
1 reviews · 0h to merge
#1688 Pin executable Hugging Face model downloads to revisions
1 round · 7 reviews · 6.5d to merge
#1684 feat: Integrate OneTrainer into Windows ROCm Helper [Windows/AMD]
5 reviews · 6.9d to merge
#1690 docs: add settings documentation, restructure env vars, update ROCm platform docs
3 reviews · 1h to merge
How this was measured
2% 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; reads 100 of 190 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Gemini CLI, Google Jules.
“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 LykosAI/StabilityMatrix 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 LykosAI/StabilityMatrix — 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