Review economics
BerriAI/litellm
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.3× the reviews submitted of the rest.
≥6%
Attributed
a floor
9
Attributed PRs
91
Other PRs
100
Read
Attributed — the latest 5
#34531 fix(responses): forward client headers to the provider on /v1/responses
4 reviews · 10.3d to merge
#34019 feat(guardrails/rubrik): prompt moderation, response-text blocking, streaming buffer, failure logging
38 reviews · 14.1d to merge
#35722 feat(guardrails/rubrik): prompt moderation, response-text blocking, streaming buffer, failure logging
4 reviews · 1h to merge
#35704 fix(openai): drop the undefined Union from owns_wrapped_http_client
1 reviews · 0h to merge
#34588 fix(proxy): backfill null user_email on existing users during JWT auth
11 reviews · 9.8d to merge
The rest — the latest 5
#34029 fix(proxy): make /cursor/chat/completions work with Cursor agent mode
1 round · 26 reviews · 14.9d to merge
#35732 fix(e2e): make spend-counter redis connection env-driven for non-cluster deployments
1 reviews · 15h to merge
#35729 feat(ui): add admin-configurable user banner
11 reviews · 15h to merge
#34971 fix(groq): translate web_search_options to the browser_search tool
3 reviews · 6.9d to merge
#35492 fix(caching): close evicted LLM clients so their connections are reclaimed
8 reviews · 2.0d to merge
How this was measured
6% 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 13794 merged PRs — the rest have not been analyzed yet.
Detected: Cursor agent, Claude Code, Devin.
“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