Review economics
crewAIInc/crewAI
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 4.5× the reviews submitted of the rest.
≥25%
Attributed
a floor
20
Attributed PRs
80
Other PRs
100
Read
Attributed — the latest 5
#6800 fix(ci): correctly skip code CI for docs-only PRs
2 reviews · 2h to merge
#6791 feat: add project_id to link OSS usage to an enterprise account
34 reviews · 5h to merge
#6779 feat: surface AMP in AGENTS.md and detect coding agents in telemetry
15 reviews · 27h to merge
#6727 feat(tracing): collect skill usage events
10 reviews · 11h to merge
#6712 feat(tools): surface tool failures instead of reporting them as success
83 reviews · 20h to merge
The rest — the latest 5
#6807 chore(ci): group uv patch/minor Dependabot updates
1 reviews · 0h to merge
#6805 feat: track interception-hook dispatches in telemetry
1 reviews · 0h to merge
#6802 fix(deps): bump aiohttp and cryptography to resolve six GHSA advisories
1 reviews · 1h to merge
#6793 fix(flow): report the real CEL error for failures inside map literals
4 reviews · 1h to merge
#5885 feat(crewai-tools): add IBM Db2 search tool
1 round · 35 reviews · 71.3d to merge
How this was measured
25% 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 2067 merged PRs — the rest have not been analyzed yet.
Detected: Cursor agent, Claude Code, Devin, GitHub Copilot coding 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 crewAIInc/crewAI 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 crewAIInc/crewAI — 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