Review economics
zylon-ai/private-gpt
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.8× the reviews submitted of the rest.
≥4%
Attributed
a floor
4
Attributed PRs
96
Other PRs
100
Read
Attributed — the latest 4
#2303 docs: add DaoXE OpenAI-compatible gateway configuration example
1 reviews · 3.8d to merge
#2271 perf(prompts): use date-level current_date to preserve prompt-prefix caching
1 reviews · 1h to merge
#2247 chore: update github actions
2 reviews · 2h to merge
#2234 chore: update dockerfile
2 reviews · 0h to merge
The rest — the latest 5
#2324 chore(deps): update Claude specs and anthropic SDK
2 reviews · 28h to merge
#2326 fix: split celery task in two (parser & store), and reuse in the attach documents
4 reviews · 2h to merge
#2325 fix: mcp oauth error
2 reviews · 1h to merge
#2323 fix: context stack
3 reviews · 1h to merge
#2322 fix: improve perf
2 reviews · 0h 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; reads 100 of 301 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, GitHub Copilot coding 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 zylon-ai/private-gpt 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 zylon-ai/private-gpt — 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