Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

alibaba/open-code-review ↗

alibaba/open-code-review AI coding statistics: 2.8%

of 683 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.8% agent · top contributor 10.5%17 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

19
agent commits
664
other considered commits
17
agent contributors
10.5%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

19assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-050%46
2026-063.1%192
2026-071.6%192
2026-085.2%191
2026-090%62

Peak month: 5.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic131.9%
Cursor AgentAnysphere50.7%
OpenAI CodexOpenAI10.1%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • a6624008 on GitHubfeat(agent): group semantically related files for multi-file review (#808)Claude Code
  • 9c5e90d0 on GitHubfeat(providers): add AWS Bedrock as a built-in provider with native SigV4 Claude Code
  • 144607f8 on GitHubfeat(llm): task-scoped session affinity for prompt caching (#332)Claude Code
  • 18f83498 on GitHubdocs(cli): align --max-tools help text with min 50 clamp (#1077)Cursor Agent
  • 48eb444a on GitHubci(pages): add smoke test step to verify build output is servable (#741)Cursor Agent
  • e75601d2 on GitHubfeat(examples/gitlab): add fail-open category/severity publication controlCursor Agent
  • 389a6e3f on GitHubfix(pages): scroll docs deep links on load (#413)OpenAI Codex
  • a53b16cf on GitHubfix(agent): stop leaking {{plan_guidance}} into MAIN_TASK prompts (#33)GitHub Copilot

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window697
Merge commits removed−3
CI / dependency bots removed−11
Considered683

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
alibaba/open-code-review
Default branch
main
Resolved HEAD
f1101fd7f51304c82e4a4f292bbee88aea0823cf ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortGo · 132 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 62 of 194 ecosystem repositories excluded
Agent-commit share position50th percentile

Midrank percentile; equal shares split the tied positions.

Repository
2.8%
Cohort median
2.8%
Share rank
66 / 132
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 132.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli alibaba/open-code-review

Scan another repository

Try