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

TryGhost/Ghost ↗

TryGhost/Ghost AI coding statistics: 0.4%

of 3,675 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.4% agent · top contributor 26.7%7 contributors
team

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

15
agent commits
3,660
other considered commits
7
agent contributors
26.7%
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

15assisted
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
2026-021.4%430
2026-030%389
2026-040%402
2026-050.2%424
2026-060.5%564
2026-070.2%564
2026-080.5%605
2026-090.3%297

Peak month: 1.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic90.2%
Cursor AgentAnysphere50.1%
GitHub CopilotGitHub10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 33f6d329 on GitHubAdded "in progress run count" stat to automation browse endpoint (#30072)Claude Code
  • 17737482 on GitHubAdded "total run count" stat to automation browse endpoint (#30037)Claude Code
  • 7eafbd28 on GitHubFixed profile card image copy in ActivityPub preferences (#29173)Claude Code
  • b79666a3 on GitHubAdded nullable posts.auto_excerpt and posts.reading_time columns (#30587)Cursor Agent
  • 00464ec9 on GitHubAdded agent payments for premium markdown URLs (#29840)Cursor Agent
  • 884aebad on GitHubFixed SharedStorage deprecation warning caused by sodo-search (#26416)Cursor Agent
  • c15e7a19 on GitHubFixed flaky automations E2E test (another attempt) (#28552)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 window4,680
Merge commits removed−15
CI / dependency bots removed−990
Considered3,675

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
TryGhost/Ghost
Default branch
main
Resolved HEAD
c040b5dfc7c827afefb93c4fc626c0ef4f079eba ↗
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.

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 position18th percentile

Midrank percentile; equal shares split the tied positions.

Repository
0.4%
Cohort median
5.4%
Share rank
306 / 376
0th50th100th

Percentile = (repositories below + half of 6 tied repositories) ÷ 376.

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 TryGhost/Ghost

Scan another repository

Try