Review economics
m87-labs/moondream
Read from the 70 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.0× the reviews submitted of the rest.
≥12%
Attributed
a floor
8
Attributed PRs
62
Other PRs
70
Read
Attributed — the latest 5
#287 I ran black on all Python files in the repository to ensure consisten…
0 reviews · 1h to merge
#233 Update README: Simplify transformers usage example
0 reviews · 0h to merge
#234 Switch to torch.inference_mode() for better performance
0 reviews · 0h to merge
#185 Use pyvips for image resizing
0 reviews · 0h to merge
#182 fix: improve Node.js client streaming implementation
0 reviews · 0h to merge
How this was measured
12% 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: Google Jules, OpenHands.
“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 m87-labs/moondream 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 m87-labs/moondream — 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