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

Eugeny/tabby ↗

Eugeny/tabby AI coding statistics: 6.4%

of 157 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
6.4% agent · top contributor 20%9 contributors
org-wide

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

10
agent commits
147
other considered commits
9
agent contributors
20%
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

10assisted
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
2026-020%7
2026-030%2
2026-0433.3%9
2026-052.3%43
2026-060%22
2026-070%27
2026-0912.8%47

Peak month: 33.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic53.2%
GitHub CopilotGitHub42.5%
Cursor AgentAnysphere10.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7e26a579 on GitHubfeat(ssh): option to reopen duplicated/restored tabs in the last working dClaude Code
  • 9cd1697f on GitHubfeat(terminal): add insert-new-line hotkey (#11346)Claude Code
  • 8d89013e on GitHubFix Windows-only plugin install failures via broken postinstall/prepare scClaude Code
  • 2af22b99 on GitHubFix PowerShell 7 (pwsh) detection for Microsoft Store/MSIX installs (#1165GitHub Copilot
  • cdae0b6e on GitHubFix WSL sessions not starting in home directory on newer Windows builds (#GitHub Copilot
  • b82ac4c9 on GitHubMake macOS build fail if code signing fails (#11255)GitHub Copilot
  • ea801300 on GitHubFlash taskbar/dock icon when the terminal bell rings (#11651)Cursor 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 window170
Merge commits removed−4
CI / dependency bots removed−9
Considered157

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
Eugeny/tabby
Default branch
master
Resolved HEAD
89c94478d41fde7b3c20566302f9122a4fd48a18 ↗
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 position54th percentile

Midrank percentile; equal shares split the tied positions.

Repository
6.4%
Cohort median
5.4%
Share rank
175 / 376
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 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 Eugeny/tabby

Scan another repository

Try