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.

OsmAnd

01Result

osmandapp/OsmAnd ↗

osmandapp/OsmAnd AI coding statistics: 4.7%

of 1,961 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

4.7% agent · top contributor 41.3%11 contributors

org-wide

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

agent commits

1,869

other considered commits

agent contributors

41.3%

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

92assisted

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: 28.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	82	4.2%
Cursor Agent	Anysphere	10	0.5%

03Evidence

Inspect the matches

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

Matched commit samples

82810c5b on GitHubRemove the office_yes phraseClaude Code
385d0e35 on GitHubAdd phrases for new POI typesClaude Code
9830a420 on GitHubOpen read-only GPX database connections read-only (OsmAnd-Issues #3331)Claude Code
6418da6f on GitHubMake offline forecast cache entries and progress updates thread-safeCursor Agent
fb4e2d3e on GitHubCreate local SimpleDateFormat instances instead of ThreadLocalCursor Agent
55cd95c0 on GitHubUse AtomicInteger for NavigationService usage bitmask updatesCursor 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 window	4,206
Merge commits removed	−819
CI / dependency bots removed	−1,426
Considered	1,961

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Java AI coding statisticsCompare evidence across Java 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 osmandapp/OsmAnd

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	206
2026-03	0%	233
2026-04	0%	215
2026-05	0%	117
2026-06	3.1%	322
2026-07	0.8%	376
2026-08	1.3%	227
2026-09	28.7%	265