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

kovidgoyal/kitty ↗

kovidgoyal/kitty AI coding statistics: 12.9%

of 1,779 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12.9% agent · top contributor 89.6%13 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

230
agent commits
1,549
other considered commits
13
agent contributors
89.6%
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

24assisted
206autonomous

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
2026-0150%2
2026-0212.1%173
2026-0318.2%297
2026-0419.4%324
2026-0520.5%229
2026-0621.2%99
2026-0713.6%103
2026-081.4%495
2026-093.5%57

Peak month: 50%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub20711.6%
Claude CodeAnthropic231.3%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • a31f9e52 on GitHubRefactor kitty_tests: move __init__.py code to base.py, update all importsGitHub Copilot
  • a36b259d on GitHubFix parser to strip semicolons from module/import names; update testsGitHub Copilot
  • d8041066 on GitHubAdd slang parser corner case tests and implement test_slang_orderingGitHub Copilot
  • 8b564c70 on GitHubGo shlex: Do not drop empty quoted stringsClaude Code
  • 0791b39a on GitHubFix completion after a trailing space in the kitty shellClaude Code
  • 2dbe5df2 on GitHubWayland: fix crash when an output global is removedClaude Code
  • 98366076 on GitHubfix(wayland): detect start_drag silently ignored by the compositorCursor 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 window2,137
Merge commits removed−310
CI / dependency bots removed−48
Considered1,779

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
kovidgoyal/kitty
Default branch
master
Resolved HEAD
1d67ecd47c0bd68951868c363baa92039d936572 ↗
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 position69th percentile

Midrank percentile; equal shares split the tied positions.

Repository
12.9%
Cohort median
6.3%
Share rank
78 / 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 kovidgoyal/kitty

Scan another repository

Try