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.

A rootless Android app that boots Alpine Linux: run containers (Podman/Docker/LXC) and GUI desktop apps.

01Result

ExTV/Podroid ↗

ExTV/Podroid AI coding statistics: 3.1%

of 392 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.1% agent · top contributor 66.7%3 contributors
individual

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

12
agent commits
380
other considered commits
3
agent contributors
66.7%
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

12assisted
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
2026-030%11
2026-047.2%111
2026-050%192
2026-0610.3%29
2026-072.9%34
2026-080%13
2026-090%2

Peak month: 10.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic82%
GitHub CopilotGitHub30.8%
Cursor AgentAnysphere10.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 21945db8 on GitHubBump to v1.0.8: Android 8+ support and lint cleanupClaude Code
  • d3be5e96 on GitHubBump version to 1.0.7 with QEMU 11 rebuild, perf improvements, and server Claude Code
  • 3f7d19de on GitHubBump version to 1.0.6 with notifications, storage permission, and boot fixClaude Code
  • 580fb26e on GitHubfix(build): fix devtmpfs boot panic, Dockerfile heredoc parse error, and AGitHub Copilot
  • be5c4da1 on GitHubfix(build): add .gitattributes to enforce LF line endings for Linux scriptGitHub Copilot
  • 41c305c9 on GitHubfeat: add Android 8 (API 26) support with iconv shimGitHub Copilot
  • 7373d8ac on GitHubfeat: added backup, load balancer, statusCursor 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 window396
Merge commits removed−4
CI / dependency bots removed−0
Considered392

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 →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 ExTV/Podroid

Scan another repository

Try