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

wshobson/agents ↗

wshobson/agents AI coding statistics: 8.8%

of 273 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8.8% agent · top contributor 20.8%11 contributors
org-wide

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

24
agent commits
249
other considered commits
11
agent contributors
20.8%
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
5autonomous

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
2026-023.7%27
2026-035.7%53
2026-0417.9%39
2026-0516.7%66
2026-062.9%35
2026-075.9%17
2026-080%27
2026-090%9

Peak month: 17.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic186.6%
GitHub CopilotGitHub62.2%
Cursor AgentAnysphere10.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 5c4a805e on GitHubfile-conversion: fix base64 argv limit, harden output path, update countsClaude Code
  • 56ba12c1 on GitHubfix: update agent and skill counts in marketplace metadataClaude Code
  • c8e2c8dd on GitHubfix: restore license field in SKILL.md lost during rebaseClaude Code
  • f5ad900e on GitHubcopilot: symlink command directories to ~/.copilot/<plugin>/commands/GitHub Copilot
  • 9a178cb0 on GitHubcopilot: ensure command frontmatter has description (synthesize from H1 whGitHub Copilot
  • 52ced895 on GitHubAutomate Copilot cache clearing in install processGitHub Copilot
  • 2f9990dd on GitHubAdd operating-kit plugin: session lifecycle, code-review, deploy, prod-logCursor Agent

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 window364
Merge commits removed−55
CI / dependency bots removed−36
Considered273

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
wshobson/agents
Default branch
main
Resolved HEAD
4236bb91f8395b0435f1d8b8baf9e8e4c69a8620 ↗
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.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position57th percentile

Midrank percentile; equal shares split the tied positions.

Repository
8.8%
Cohort median
6.3%
Share rank
106 / 247
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

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 →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 wshobson/agents

Scan another repository

Try