Review economics
xorbitsai/inference
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.8× the reviews submitted of the rest.
≥10%
Attributed
a floor
14
Attributed PRs
86
Other PRs
100
Read
Attributed — the latest 5
#5281 fix: add anthropic SDK to core dependencies for route registration
2 reviews · 17h to merge
#5264 perf(supervisor): add whole-result debounce cache for list_models
3 reviews · 6h to merge
#5255 fix(webui): improve worker node display in multi-select
4 reviews · 7h to merge
#5246 feat(webui): support multi-node selection in log center
2 reviews · 2h to merge
#5243 feat(frontend): auto-reload shell routes on export directory change
4 reviews · 2h to merge
The rest — the latest 5
#5230 feat: add DeepDoc (ragflow) OCR model as builtin image model
1 round · 7 reviews · 13.8d to merge
#5270 feat(sglang): surface logprobs in /v1/completions and /v1/chat/completions
8 reviews · 3.3d to merge
#5274 docs: add v3.1.0 to release notes index
2 reviews · 45h to merge
#5280 feat: PDF input support for the OCR API
5 reviews · 21h to merge
#5279 ENH: update models JSON [rerank]
1 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; 2 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 2092 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex, Gemini CLI.
“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 xorbitsai/inference 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 xorbitsai/inference — 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