Review economics
AlexsJones/llmfit
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.3× the reviews submitted of the rest.
≥31%
Attributed
a floor
32
Attributed PRs
68
Other PRs
100
Read
Attributed — the latest 5
#792 fix(hardware): detect Jetson/Tegra Orin iGPU as unified memory
1 reviews · 7.4d to merge
#750 ci(docker): build arm64 image natively instead of under QEMU
0 reviews · 0h to merge
#760 fix(tui): force a full clear after entering the alternate screen
0 reviews · 30h to merge
#761 feat(api): unify fit envelope serializers, exposing parity fields on REST/MCP
2 reviews · 25h to merge
#758 feat(api): expose usable_context and effective_context_length in the models envelope
1 round · 3 reviews · 34h to merge
The rest — the latest 5
#829 [Automated] Weekly model data refresh
1 reviews · 17h to merge
#828 [Automated] Weekly benchmark cache refresh
1 reviews · 18h to merge
#827 chore(main): release 1.1.8
0 reviews · 18h to merge
#784 chore(main): release 1.1.7
1 reviews · 12.7d to merge
#822 bench: community results for apple-m5-max
1 reviews · 17h to merge
How this was measured
31% 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 397 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, 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 AlexsJones/llmfit 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 AlexsJones/llmfit — 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