Review economics
HKUDS/DeepTutor
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.9× the time to merge of the rest.
≥6%
Attributed
a floor
9
Attributed PRs
91
Other PRs
100
Read
Attributed — the latest 5
#748 fix(visualize): guard against invalid visual_genre crashing generation
0 reviews · 44h to merge
#703 fix(llm): add opus-5 to the Anthropic effort-based family list
0 reviews · 22h to merge
#675 fix(json_parser): strip <think> reasoning tags before parsing
0 reviews · 5h to merge
#617 fix: count streamed LLM usage once per completion
0 reviews · 8.2d to merge
#615 fix(webui): send edited user message on Enter, keep Shift+Enter as newline
0 reviews · 9.1d to merge
The rest — the latest 5
#730 fix: bootstrap persisted interface language on first load
0 reviews · 3.5d to merge
#744 feat(embedding): support Gemini Embedding 2 native RAG
0 reviews · 48h to merge
#736 feat: add per-model reasoning effort setting
0 reviews · 3.2d to merge
#743 fix: make local container Codex OAuth bridge temporary
0 reviews · 2.0d to merge
#746 Add Novita AI as a provider option
0 reviews · 45h to merge
How this was measured
6% 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; 6 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 223 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, Claude Code, GitHub Copilot coding agent, Cursor 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 HKUDS/DeepTutor 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 HKUDS/DeepTutor — 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