Review economics
OpenHands/OpenHands
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.1× the reviews submitted of the rest.
≥11%
Attributed
a floor
48
Attributed PRs
52
Other PRs
100
Read
Attributed — the latest 5
#16276 feat: home automations dashboard
2 reviews · 16h to merge
#16211 feat(backends): compact Cloud vs Agent-server add-backend chooser
1 reviews · 10h to merge
#16142 fix(chat): allow dismissing failed pending user messages
3 reviews · 2.7d to merge
#16214 refactor(types): use client error events
4 reviews · 23h to merge
#16163 docs: fix runtime modes table in architecture doc
2 reviews · 2.5d to merge
The rest — the latest 5
#16264 fix: resolve npm audit vulnerabilities
3 reviews · 21h to merge
#16290 fix: use IPv4 loopback for local proxy targets
2 reviews · 2h to merge
#16243 fix(backends): pin backend identity on sidebar conversation links
1 reviews · 47h to merge
#16249 chore(deps): bump the i18next group across 1 directory with 3 updates
1 reviews · 19h to merge
#16254 chore(deps): bump monaco-editor from 0.55.1 to 0.56.0 in the monaco group across 1 directory
1 reviews · 19h to merge
How this was measured
11% 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 7417 merged PRs — the rest have not been analyzed yet.
Detected: Cursor agent, OpenHands, Devin, OpenAI Codex, 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 OpenHands/OpenHands 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 OpenHands/OpenHands — 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