Review economics
stanfordnlp/dspy
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.7× the reviews submitted of the rest.
≥18%
Attributed
a floor
25
Attributed PRs
75
Other PRs
100
Read
Attributed — the latest 5
#10139 fix(dspy): repair ReAct error formatter after parallel merges
0 reviews · 1h to merge
#10132 fix(dspy): preserve typed ReAct context window errors
0 reviews · 0h to merge
#10134 fix(dspy): root CodeInterpreterError under DSPyError
0 reviews · 0h to merge
#10135 refactor(dspy): share LM-facing exception formatting
0 reviews · 0h to merge
#10129 fix(deps): cap FastAPI for LiteLLM proxy
0 reviews · 0h to merge
The rest — the latest 5
#10151 fix: cap FastAPI for LiteLLM proxy compatibility
0 reviews · 10h to merge
#10131 test(dspy): repair dead assertions in settings thread/async ownership tests
0 reviews · 0h to merge
#10047 feat(dspy.Flex) + GEPA extension
20 reviews · 19.7d to merge
#10059 chore(deps): bump mistune from 3.2.1 to 3.3.3 in /docs
0 reviews · 10.8d to merge
#10077 chore(deps): bump mkdocstrings from 1.0.4 to 1.0.6 in /docs
0 reviews · 3.8d to merge
How this was measured
18% 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; 4 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 1675 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, Amp, Claude Code, Devin.
“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 stanfordnlp/dspy 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 stanfordnlp/dspy — 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