Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

A persistent workspace for development work that self-improves and continues beyond one session.

01Result

kirodotdev/KiroCrew ↗

kirodotdev/KiroCrew AI coding statistics: 1.9%

of 6,133 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.9% agent · top contributor 69.2%9 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

117
agent commits
6,016
other considered commits
9
agent contributors
69.2%
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

117assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-060%334
2026-070%789
2026-082.3%3357
2026-092.4%1653

Peak month: 2.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1111.8%
Cursor AgentAnysphere50.1%
GitHub CopilotGitHub10%

03Evidence

Inspect the matches

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

Matched commit samples

  • f2d80ab2 on GitHubfix(messaging): apply the channel-ID cap at the two uncapped call sites (#Claude Code
  • 6163d9a9 on GitHubfix(chat): write an attachment destination the markdown reader resolves (#Claude Code
  • cbeeb48b on GitHubfix(issue-radar): read a non-object cache file as a miss (#10779)Claude Code
  • 8ed028b0 on GitHubfix(spec-builder): close delete, review, and i18n gaps (#5111)Cursor Agent
  • 4af4efb5 on GitHubfix(security): lock remaining secret writers down before publish (#5709)Cursor Agent
  • d3af17cf on GitHubfix(i18n): gate confirm interpolations so a bare operand cannot ship (#567Cursor Agent
  • dd2fee85 on GitHubdocs: add Teams Git installation options (#5350)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 window6,300
Merge commits removed−124
CI / dependency bots removed−43
Considered6,133

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

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 →Python AI coding statisticsCompare evidence across Python repositories →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 kirodotdev/KiroCrew

Scan another repository

Try