Review economics
CherryHQ/cherry-studio
Read from the 100 most recently merged pull requests · · read 2 times
Pull requests with attributed agent authorship took only 0.4× the reviews submitted of the rest.
≥10%
Attributed
a floor
6
Attributed PRs
94
Other PRs
100
Read
Attributed — the latest 5
#17901 fix(provider-registry): serve DeepSeek V4 models over the Anthropic endpoint
2 reviews · 0h to merge
#17840 fix(topic-naming): stop inheriting assistant reasoning effort and restore model selector
2 reviews · 9h to merge
#17841 fix(agents-migration): copy shared v1 workspace once into the latest session
2 reviews · 8h to merge
#17798 fix(knowledge): prevent crash when refreshing knowledge item
2 reviews · 8h to merge
#17783 fix(chat-scroll): unify streaming follow state
2 reviews · 18h to merge
The rest — the latest 5
#17930 feat(conversation-picker): keep the create row visible while searching
3 reviews · 3h to merge
#14988 feat: Add 'embedding' endpoint type for NEWAPI model configuration
5 reviews · 86.6d to merge
#17934 chore(deps): upgrade selection-hook to 2.0.3
2 reviews · 1h to merge
#17929 fix(api-gateway): normalize internal Agent continuations
2 reviews · 1h to merge
#17931 fix(resource-pagination): avoid redundant first-page requests
2 reviews · 0h to merge
How this was measured
10% 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; 10 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 4508 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, 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 CherryHQ/cherry-studio 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 CherryHQ/cherry-studio — 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