Review economics
tinyhumansai/openhuman
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.9× the review rounds of the rest.
≥3%
Attributed
a floor
6
Attributed PRs
94
Other PRs
100
Read
Attributed — the latest 5
#5367 fix(voice): stop the Piper voice id leaking into non-Piper TTS providers
1 round · 9 reviews · 27h to merge
#5401 fix(agent): preserve chat context across a Quick/Reasoning switch
1 round · 9 reviews · 6h to merge
#5340 fix(config): surface a user notice when a corrupt config.toml is reset (#5167)
2 rounds · 19 reviews · 22h to merge
#5278 feat(agent-world): Tiny Place ledger filters + copy tx-id (#4776 §4)
1 round · 15 reviews · 3.0d to merge
#5271 feat(agent-world): Tiny Place directory search + pagination (#4776 §6)
2 rounds · 22 reviews · 3.3d to merge
The rest — the latest 5
#5414 Promote main -> release (conflict-resolved)
1 reviews · 0h to merge
#5412 feat(threads): name a thread in three words
5 reviews · 1h to merge
#5411 fix(media): error instead of false success on the generation poll timeout
1 round · 12 reviews · 4h to merge
#5407 feat(voice): ElevenLabs Voice Agents — core RPC + realtime session + local-agent relay handler (#5399)
2 rounds · 36 reviews · 6h to merge
#5402 feat(memory): warn before the embedding budget silently stops memory
4 rounds · 50 reviews · 9h to merge
How this was measured
3% 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 2914 merged PRs — the rest have not been analyzed yet.
Detected: Cursor agent, 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 tinyhumansai/openhuman 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 tinyhumansai/openhuman — 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