Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.

01Result

pinchtab/pinchtab ↗

pinchtab/pinchtab AI coding statistics: 1.6%

of 2,550 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.6% agent · top contributor 29.3%17 contributors
org-wide

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

41
agent commits
2,509
other considered commits
17
agent contributors
29.3%
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

41assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%536
2026-032.3%752
2026-040%228
2026-057.4%122
2026-060%54
2026-070.2%465
2026-082%98
2026-094.1%295

Peak month: 7.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic391.5%
GitHub CopilotGitHub20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • e249efcf on GitHubtest(report): stop the security-defaults test rewriting the real configClaude Code
  • 8a916065 on GitHubtest(config): compare fontsDir against the cleaned path, not a separatorClaude Code
  • 3334bb89 on GitHubtest(runtime): give the discovery stub a name Windows can executeClaude Code
  • 39a383c3 on GitHubUpdate internal/config/editor_set.goGitHub Copilot
  • da0e0a2c on GitHubfeat: stealth runtime v2 — structured bundle architecture (#380)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 window2,908
Merge commits removed−348
CI / dependency bots removed−10
Considered2,550

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Go AI coding statisticsCompare evidence across Go repositories →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 pinchtab/pinchtab

Scan another repository

Try