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.

DuckDuckGo Android App

01Result

duckduckgo/Android ↗

duckduckgo/Android AI coding statistics: 22.4%

of 1,742 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

22.4% agent · top contributor 33.8%28 contributors

org-wide

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

390

agent commits

1,352

other considered commits

agent contributors

33.8%

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

390assisted

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

Peak month: 34.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	363	20.8%
Cursor Agent	Anysphere	31	1.8%
GitHub Copilot	GitHub	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

07c41b9c on GitHubUpdate password import onboarding pixels (#9746)Claude Code
3d015342 on GitHubAdd metrics for the passwords import onboarding experiment (#9743)Claude Code
8b013e50 on GitHubMove Google passwords import pixels to the import web flow (#9674)Claude Code
7727d33c on GitHubAllow broken-site prompt on user-unprotected sites (#9466)Cursor Agent
73470760 on GitHubFix broken site refresh detection timing (#9460)Cursor Agent
d8847604 on GitHubAdd contentScopeExperiment001-100 toggles (#9485)Cursor Agent
668a81ca on GitHubMove stacked PRs to Waiting for release when merged via the queue (#9650)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 window	1,887
Merge commits removed	−106
CI / dependency bots removed	−39
Considered	1,742

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 duckduckgo/Android

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	1.2%	162
2026-03	15.4%	240
2026-04	16.9%	178
2026-05	22.3%	282
2026-06	34.7%	262
2026-07	26.5%	272
2026-08	31.3%	230
2026-09	19.8%	116