Review economics
lobehub/lobehub
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.5× the reviews submitted of the rest.
≥32%
Attributed
a floor
33
Attributed PRs
67
Other PRs
100
Read
Attributed — the latest 5
#17889 ✨ feat(chat): let the client mint topic and message ids
1 reviews · 16h to merge
#17893 ✨ feat(server): add missing temporal placeholder generators for server-side runs
2 reviews · 12h to merge
#17894 ✨ feat(agent): compose random names, richer @ mention rows, dice roll in identity form
1 reviews · 0h to merge
#17888 🔖 chore(cli): bump version to 0.0.47
0 reviews · 6h to merge
#17885 💄 style(home): fold the rail's sections into the main column when it collapses
1 reviews · 7h to merge
The rest — the latest 5
#17805 🐛 fix(task): seed heartbeat schedule lifecycle
1 reviews · 3.4d to merge
#17907 ✨ feat(hetero-agent): add Codex app-server runtime lab
0 reviews · 1h to merge
#17808 🐛 fix: populate workingDirectory in local agent builtin tool dispatch
1 reviews · 3.1d to merge
#17899 ✨ feat(hetero-agent): add Pi coding agent support
0 reviews · 1h to merge
#17860 🐛 fix: preserve active branch and provider failure evidence
7 reviews · 22h to merge
How this was measured
32% 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; 3 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 7509 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex.
“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 lobehub/lobehub 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 lobehub/lobehub — 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