Review economics
OpenBMB/VoxCPM
Read from the 25 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.5× the reviews submitted of the rest.
≥11%
Attributed
a floor
3
Attributed PRs
22
Other PRs
25
Read
Attributed — the latest 3
The rest — the latest 5
#355 docs: add audio.cpp to Ecosystem & Community (EN/ZH)
0 reviews · 0h to merge
#348 docs: add llama.cpp-omni on-device inference section
1 reviews · 4h to merge
#327 feat: Add Seed Support for Reproducible Voice Generation (v1 & v2)
1 reviews · 27.4d to merge
#329 Fix load saved lora_config.json when loading LoRA weights
1 reviews · 24.1d to merge
#332 Add optional post-generation timestamp alignment
1 reviews · 22.9d to merge
How this was measured
11% 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.
Detected: Claude Code.
“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 OpenBMB/VoxCPM 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 OpenBMB/VoxCPM — 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