Review economics
BerriAI/litellm
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.9× the reviews submitted of the rest.
≥4%
Attributed
a floor
7
Attributed PRs
93
Other PRs
100
Read
Attributed — the latest 5
#34957 fix(cost): bill gpt-5.6 prompt cache reads at the cache read rate
7 reviews · 7.7d to merge
#35859 feat(ui): add Test Routing to the auto router create form
5 reviews · 2h to merge
#35726 fix(s3_v2): sign S3 object URLs with S3SigV4Auth so encoded paths verify
2 reviews · 25h to merge
#35738 fix(bedrock): drop conflicting tool_choice.type when toolConfig.toolChoice is set
1 reviews · 18h to merge
#35555 feat(gemini): add gemini-robotics-er-2-preview and gemini-robotics-er-1.6-preview
3 reviews · 2.8d to merge
The rest — the latest 5
#35976 fix(docker): bake the pip image's prisma engines at a world-readable path
2 reviews · 1h to merge
#35855 feat(auto-router): let operators replace the LLM classifier's system prompt
13 reviews · 20h to merge
#35717 feat(sgr): make the gateway middleware the source of truth for successful requests
12 reviews · 44h to merge
#35926 chore(lint): remove litellm/types from the ruff lint exclusion
3 reviews · 11h to merge
#35837 fix(proxy): keep the connected DB client when a startup health check fails
1 reviews · 21h to merge
How this was measured
4% 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 13870 merged PRs — the rest have not been analyzed yet.
Detected: Cursor agent, Devin, 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 BerriAI/litellm 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 BerriAI/litellm — 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