Review economics
Significant-Gravitas/AutoGPT
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.6× the reviews submitted of the rest.
≥40%
Attributed
a floor
38
Attributed PRs
62
Other PRs
100
Read
Attributed — the latest 5
#13591 fix(backend): exclude soft-deleted orgs from org migration backfill JOINs
1 reviews · 19.5d to merge
#13332 fix(backend/copilot): stop empty untitled dream sessions polluting the chat list
21 reviews · 55.3d to merge
#13338 fix(backend/copilot): dream runtime correctness — phase timeouts, ingestion drain, honest registration
46 reviews · 54.8d to merge
#13434 ci(platform): add on-demand backend CI run (workflow_dispatch) with optional PR coverage refresh
7 reviews · 40.5d to merge
#13391 fix(backend/copilot): drop transient-intent + generic-knowledge from dream memory
23 reviews · 47.1d to merge
The rest — the latest 5
#13764 feat(platform): voice brain-dump onboarding step
177 reviews · 2.9d to merge
#13751 refactor(frontend): replace Phosphor icons with Hugeicons stroke-rounded
8 reviews · 3.9d to merge
#12702 fix(backend): add SSRF protection and download limits to VideoDownloadBlock
2 rounds · 16 reviews · 119.1d to merge
#13627 feat(backend): single-source LLM model catalog (cutover + Kimi K3)
287 reviews · 14.6d to merge
#13767 fix(frontend): prevent translation extensions from breaking TourChatHeader button
1 reviews · 26h to merge
How this was measured
40% 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; 2 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 4700 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, GitHub Copilot coding agent, OpenAI Codex, 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 Significant-Gravitas/AutoGPT 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 Significant-Gravitas/AutoGPT — 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