Review economics
MervinPraison/PraisonAI
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.3× the reviews submitted of the rest.
≥4%
Attributed
a floor
5
Attributed PRs
95
Other PRs
100
Read
Attributed — the latest 5
#3695 fix(claude-code): live progress from stream-json + on_event callback
4 reviews · 2h to merge
#3676 ci(release): harden the release pipeline + first-class single-package releases
2 reviews · 1h to merge
#3628 ci(release): name the packages in the safety-net commit message
1 reviews · 0h to merge
#3575 ci(release): scope the release app token to this repository
2 reviews · 0h to merge
#3572 ci(release): single commit per release, authored by praisonai-triage-agent[bot]
4 reviews · 1h to merge
The rest — the latest 5
#3678 fix: hierarchical return, shared-memory data loss, per-agent approval scope
2 reviews · 12h to merge
#3698 refactor: DRY ContextConfig→ManagerConfig mapping in Agent.context_manager
1 reviews · 2h to merge
#3699 fix: remove dead FunctionTool.get_schema override
0 reviews · 1h to merge
#3690 feat: add read-only agent-callable gateway_status tool
1 reviews · 2h to merge
#3693 feat: no-LLM command action for scheduler jobs
3 reviews · 1h 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; 90 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 1993 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Cursor agent.
“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 MervinPraison/PraisonAI 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 MervinPraison/PraisonAI — 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