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.

Android application for Meshtastic

01Result

meshtastic/Meshtastic-Android ↗

meshtastic/Meshtastic-Android AI coding statistics: 35.6%

of 1,626 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
35.6% agent · top contributor 91.5%15 contributors
individual

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

579
agent commits
1,047
other considered commits
15
agent contributors
91.5%
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

569assisted
10autonomous

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
2026-021.3%156
2026-030.6%169
2026-0427.4%208
2026-0557.8%166
2026-0663.9%191
2026-0751.4%317
2026-0842.4%314
2026-094.8%105

Peak month: 63.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic42426.1%
GitHub CopilotGitHub16210%

03Evidence

Inspect the matches

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

Matched commit samples

  • fecc241b on GitHubfix(takserver): skip compressed v1 TAK packets to stop duplicate contacts Claude Code
  • 60019db9 on GitHubfeat(ui): blend noise floor into signal quality rating (design#15) (#7009)Claude Code
  • ea5fd329 on GitHubfix(settings): floor the beacon broadcast-target list at one row (#7010)Claude Code
  • 0595852a on GitHubRemove stale Vico workaround and close dependency-upgrade follow-ups (#702GitHub Copilot
  • ae3e3d29 on GitHubfix(notifications): open node detail when tapping 'New Node Seen' notificaGitHub Copilot
  • 35fba4d5 on GitHubfix(ble): Harden BLE connection lifecycle (#5795)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 window2,384
Merge commits removed−1
CI / dependency bots removed−757
Considered1,626

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 →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 meshtastic/Meshtastic-Android

Scan another repository

Try