Review economics
NousResearch/hermes-agent
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.0× the time to merge of the rest.
≥2%
Attributed
a floor
3
Attributed PRs
97
Other PRs
100
Read
Attributed — the latest 3
#77334 fix(compression): pass overhead-aware token size to overflow-recovery compression
0 reviews · 0h to merge
#77324 fix(tui): snapshot history after pending model switch applies (#76870)
0 reviews · 0h to merge
#77355 perf(tts): pipeline sync per-sentence synthesis with playback (#74301 salvage)
0 reviews · 0h to merge
The rest — the latest 5
#69416 feat(observability): add Relay active install metrics
0 reviews · 14.1d to merge
#68978 feat(observability): add Relay client resource metrics
3 reviews · 14.8d to merge
#68883 feat(observability): aggregate bounded skill metrics
0 reviews · 14.9d to merge
#79521 fmt(js): `npm run fix` auto-fix
0 reviews · 0h to merge
#79513 fix(desktop): stop reporting false failure on successful backend updates
0 reviews · 0h to merge
How this was measured
2% 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 9926 merged PRs — the rest have not been analyzed yet.
Detected: 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 NousResearch/hermes-agent 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 NousResearch/hermes-agent — 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