Review economics
RunanywhereAI/runanywhere-sdks
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 1.0× the reviews submitted of the rest.
≥15%
Attributed
a floor
19
Attributed PRs
81
Other PRs
100
Read
Attributed — the latest 5
#618 fix(sdks): PR #605 review follow-ups (rag.search ABI + cross-SDK parity)
3 reviews · 1h to merge
#607 llm: constrained tool-call decoding, parallel tool calls, agent-loop wiring
3 reviews · 1h to merge
#599 Centralize SDK defaults in idl/sdk_defaults.proto and fix the drift they had accumulated
3 reviews · 8h to merge
#593 fix: unblock main SwiftLint/ktlint
0 reviews · 9h to merge
#583 NVIDIA family (unified): capabilities + catalogs + Cosmos3-Edge
10 reviews · 2.4d to merge
The rest — the latest 5
#619 NeuRT: Apple Neural Engine as a first-class engine (coreml -> neurt), and a CI-buildable shell
2 reviews · 39h to merge
#628 LFM2.5-2.6B: v75/v81 NPU eligibility + llamacpp backend (release v30)
0 reviews · 0h to merge
#624 feat(npu): add LFM2.5-2.6B (HNPU) for Hexagon v79
1 reviews · 7h to merge
#627 v4 public API conformance: LoadedModel, streams, SpeechHandle, finish_reason
0 reviews · 3h to merge
#611 fix(web): keep the modality default module when a lower-priority slot survives
2 reviews · 34h to merge
How this was measured
15% 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 289 merged PRs — the rest have not been analyzed yet.
Detected: Cursor agent, Claude Code, OpenAI Codex.
“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 RunanywhereAI/runanywhere-sdks 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 RunanywhereAI/runanywhere-sdks — 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