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.

All of source code of Floorp 12, the most Advanced and Fastest Firefox derivative 🦊

01Result

Floorp-Projects/Floorp ↗

Floorp-Projects/Floorp AI coding statistics: 14.6%

of 556 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.6% agent · top contributor 34.6%8 contributors
team

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

81
agent commits
475
other considered commits
8
agent contributors
34.6%
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

81assisted
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%16
2026-0327.1%85
2026-047.1%42
2026-0515.7%83
2026-0620.5%127
2026-078.8%34
2026-084.1%147
2026-0931.8%22

Peak month: 31.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic6111%
GitHub CopilotGitHub122.2%
Cursor AgentAnysphere81.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 9c051c5d on GitHubfix(memory): cap pollIntervalSec below the 32-bit timeout limitClaude Code
  • 60d440a2 on GitHubfix(memory): type the poll timer handle and refresh the generated docsClaude Code
  • faed9088 on GitHubfix(memory): type the poll timer handle as a numberClaude Code
  • c3bbcec6 on GitHubfeat(command-palette): add documentation for default keyboard shortcut andGitHub Copilot
  • 5ef30c22 on GitHubfeat(command-palette): add 'Close Other Tabs' command with localization suGitHub Copilot
  • d9a0f2cf on GitHubfeat(command-palette): enhance container choice labels with localization sGitHub Copilot
  • e6803c76 on GitHubfix(pwa): migrate all SSB window tabs into assigned containerCursor Agent
  • b4aa3a89 on GitHubfix(test): handle nullable getComputedStyle in cssVariablesUI testCursor Agent
  • 2a152b44 on GitHubfix(test): stabilize cssVariablesUI theme variable assertion in CICursor 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 window666
Merge commits removed−75
CI / dependency bots removed−35
Considered556

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 Floorp-Projects/Floorp

Scan another repository

Try