Review economics
huggingface/tokenizers
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.2× the reviews submitted of the rest.
≥3%
Attributed
a floor
7
Attributed PRs
93
Other PRs
100
Read
Attributed — the latest 5
#2246 fix(bench): use full tokenizer configs, add gemma-4 and mistral-small-4
0 reviews · 0h to merge
#2235 feat(bindings): e2e and golden tests for Python bindings
0 reviews · 5h to merge
#2177 ci: bench against latest release, measure memory consumption and executable size
1 reviews · 20h to merge
#2146 ci: label-based trigger
0 reviews · 0h to merge
#2145 ci: maintain pipeline-bench report in PR description + comment reactions
0 reviews · 0h to merge
The rest — the latest 5
#2295 feat: gate parallelism
1 reviews · 0h to merge
#2294 fix(bpe): the byte gate classifies the delimiter, not the word
3 reviews · 0h to merge
#2262 perf(bpe): WordCache
5 reviews · 6.9d to merge
#2284 feat: re-introduce pretokens scratch buffers (`thread_local`)
2 reviews · 19h to merge
#2292 fix(python): pin the ruff rule set so a ruff release can't redden main
0 reviews · 0h to merge
How this was measured
3% 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; reads 100 of 731 merged PRs — the rest have not been analyzed yet.
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 huggingface/tokenizers 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 huggingface/tokenizers — 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