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
QwenLM/qwen-code ↗

QwenLM/qwen-code AI coding statistics: 7.7%

of 5,587 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
7.7% agent · top contributor 32.9%52 contributors
org-wide

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

432
agent commits
5,155
other considered commits
52
agent contributors
32.9%
largest contributor

What shapes this result

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

Assisted or autonomous

432assisted
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
2026-021.1%364
2026-033.1%612
2026-0433.1%493
2026-056.9%362
2026-064%767
2026-077.1%1315
2026-087.2%1068
2026-093.1%606

Peak month: 33.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic3917%
Cursor AgentAnysphere220.4%
GitHub CopilotGitHub220.4%
OpenAI CodexOpenAI10%

Inspect the matches

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

Matched commit samples

  • ac1edef9 on GitHubfix(review): keep host-trusted state out of the container's writable surfaClaude Code
  • 62d22cd4 on GitHubfix(web-shell): scope mock sessions by workspace (#10273)Claude Code
  • b7ecef62 on GitHubdocs(arena): clarify unset run limits (#9860)Claude Code
  • 43519971 on GitHubfix(artifacts): refresh updatedAt when artifact content changes (#9929)Cursor Agent
  • 4ddbf227 on GitHubfeat(mcp): add MCP 2026 core and WebShell Apps host (#8992)Cursor Agent
  • 431a0bd9 on GitHubfix(daemon): keep restored ask_user_question valid after load (#9763)Cursor Agent
  • a0bfc326 on GitHubtest: deflake write_file content assertion in tool-control E2E test (#7613GitHub Copilot
  • 86103203 on GitHubfix(cli): correct queued message display style and ordering (#7381)GitHub Copilot
  • 545e924e on GitHubfix(serve): avoid TOCTOU race dropping live sessions from list response (#GitHub Copilot
  • cffc4049 on GitHubfeat(dingtalk): show dynamic lifecycle tags (#10504)OpenAI Codex

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 window6,051
Merge commits removed−463
CI / dependency bots removed−1
Considered5,587

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

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
QwenLM/qwen-code
Default branch
main
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

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.

CohortJS/TS · 376 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 194 of 570 ecosystem repositories excluded
Agent-commit share position59th percentile

Midrank percentile; equal shares split the tied positions.

Repository
7.7%
Cohort median
5.4%
Share rank
155 / 376
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 376.

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 QwenLM/qwen-code

Scan another repository