Review economics
TabbyML/tabby
Read from the 100 most recently merged pull requests ·
Not enough merged pull requests on both sides yet to compare how they land in review.
≥1%
Attributed
a floor
0
Attributed PRs
100
Other PRs
100
Read
The rest — the latest 5
#4510 Revert "feat: add Avian as a model provider"
0 reviews · 0h to merge
#4448 feat: add Avian as a model provider
1 round · 1 reviews · 3.2d to merge
#4443 chore(ci): build cpu only tabby image
0 reviews · 10.4d to merge
#4432 docs(endpoint): add endpoint config and api usage, remove sunset features
0 reviews · 23.0d to merge
#4441 feat(usage): collect endpoint usage
0 reviews · 17h to merge
How this was measured
1% 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 3002 merged PRs — the rest have not been analyzed yet.
Detected: 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 TabbyML/tabby 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 TabbyML/tabby — 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