Review economics
kvcache-ai/ktransformers
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.5× the reviews submitted of the rest.
≥18%
Attributed
a floor
16
Attributed PRs
84
Other PRs
100
Read
Attributed — the latest 5
#2029 docs: add FAQ entry about SGLang MoE kernel config warning
1 reviews · 24.1d to merge
#2057 [docs]: clean up Qwen3.5 KT LoRA serving guide
1 reviews · 0h to merge
#2054 release: bump version to 0.6.3
1 reviews · 0h to merge
#2031 [feat](kt-lora): add end-to-end Qwen3.5 MoE KT LoRA serving workflow
6 reviews · 3.1d to merge
#2015 [feat](kt-kernel): AVX2 MXFP4 MoE MXFP4 dispatch
1 reviews · 12.0d to merge
The rest — the latest 5
#2140 Docs/dsv4 docker tutorial
0 reviews · 0h to merge
#2136 docs: add DeepSeek V4 Flash Docker guide
1 reviews · 0h to merge
#2117 [build] Sync sglang-kt submodule
0 reviews · 0h to merge
#2105 release: bump version to 0.6.4
0 reviews · 0h to merge
#2094 [feat](kt-kernel): SFT end2end
1 reviews · 4.9d to merge
How this was measured
18% 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; 1 PR came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 592 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Gemini CLI, Cursor agent, 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 kvcache-ai/ktransformers 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 kvcache-ai/ktransformers — 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