Review economics
MemPalace/mempalace
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.0× the reviews submitted of the rest.
≥14%
Attributed
a floor
20
Attributed PRs
80
Other PRs
100
Read
Attributed — the latest 5
#2127 fix(entity): defuse entity-candidate ReDoS on long ASCII runs (#2065)
1 reviews · 0h to merge
#2072 fix(mcp): self-exit on stdin EOF/broken pipe so orphaned stdio sessions release locks
0 reviews · 9.0d to merge
#2109 fix(repair): take the mine-lock before archiving in repair --mode from-sqlite
1 round · 2 reviews · 3.4d to merge
#1965 style(tests): fix ruff format check left red by #1960
0 reviews · 2.2d to merge
#1960 fix(mcp): self-heal writer lease instead of latching read-only for life
0 reviews · 6h to merge
The rest — the latest 5
#2148 fix(windows): safely repair legacy mojibake with backups
0 reviews · 14h to merge
#977 feat(searcher): wire i18n stop words into BM25 tokenizer (#973)
0 reviews · 107.4d to merge
#2137 fix(hooks): ingest only the active transcript
0 reviews · 9h to merge
#2140 fix(hooks): ingest only the active transcript (#2137)
2 reviews · 0h to merge
#2136 fix(embedding): remap unsupported EmbeddingGemma token IDs
0 reviews · 9h to merge
How this was measured
14% 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; 3 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 552 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex, Gemini CLI, Cursor 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 MemPalace/mempalace 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 MemPalace/mempalace — 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