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

CapSoftware/Cap ↗

CapSoftware/Cap AI coding statistics: 2.6%

of 4,439 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.6% agent · top contributor 71.3%10 contributors
team

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

115
agent commits
4,324
other considered commits
10
agent contributors
71.3%
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

111assisted
4autonomous

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
2026-0216.1%354
2026-032%490
2026-042.7%401
2026-051.6%634
2026-060.2%981
2026-070.6%650
2026-084.1%511
2026-090%418

Peak month: 16.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere952.1%
Claude CodeAnthropic150.3%
GitHub CopilotGitHub50.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 22afc3ff on GitHubfeat: add freehand draw tool to screenshot editor (#2136)Cursor Agent
  • 9bf57605 on GitHubfix: stop firewall probe from wiping Loom import resultsCursor Agent
  • c9f0f8d0 on GitHubfix: keep Loom import actions from returning undefinedCursor Agent
  • 3b42a0ae on GitHubfix(rendering): drive keyboard overlay from recording_time so it follows cClaude Code
  • 35243841 on GitHubfix(desktop): main-thread deadlock in macOS screen-recording permission chClaude Code
  • 264e81d4 on GitHubfix(recording): don't false-trip Windows H264 encoder timeout after a longClaude Code
  • 99c7e701 on GitHubfix: pin tauri-plugin-dialog/fs npm versions to match Rust crate versionsGitHub Copilot
  • 9fe11e35 on GitHubchore: bump desktop app version to 0.5.4GitHub Copilot
  • d0e4d65e on GitHubPotential fix for code scanning alert no. 112: Incomplete multi-character 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 window4,728
Merge commits removed−289
CI / dependency bots removed−0
Considered4,439

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
CapSoftware/Cap
Default branch
main
Resolved HEAD
94bd7b46f8cdd79d6ce0328861525b2e3f4cdf56 ↗
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.

CohortRust · 117 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 33 of 150 ecosystem repositories excluded
Agent-commit share position56th percentile

Midrank percentile; equal shares split the tied positions.

Repository
2.6%
Cohort median
2%
Share rank
52 / 117
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 117.

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 CapSoftware/Cap

Scan another repository

Try