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.

ArduPlane, ArduCopter, ArduRover, ArduSub source

01Result

ArduPilot/ardupilot ↗

ArduPilot/ardupilot AI coding statistics: 15.7%

of 3,125 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

15.7% agent · top contributor 84.5%19 contributors

individual

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

490

agent commits

2,635

other considered commits

agent contributors

84.5%

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

490assisted

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: 24.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	483	15.5%
Cursor Agent	Anysphere	5	0.2%
Gemini CLI	Google	1	0%
GitHub Copilot	GitHub	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

e8d00f39 on GitHubautotest: add AHRSExternalNoAttitudeAirspeedIndex testClaude Code
49b71e1f on GitHubautotest: add AHRSActiveAirspeedIndex testClaude Code
fbf750c2 on GitHubTools: honour MAVPROXY_CMD everywhere we run MAVProxyClaude Code
2023e51a on GitHubAP_Baro: fix MS5837 stamping BARO_DEVID with devtype 0Cursor Agent
31b247b3 on GitHubAP_NavEKF: remove unused getPosVelYawSourceSetCursor Agent
ffab968d on GitHubAP_NavEKF3: log per-core source set in XKFSCursor Agent
7af4ce12 on GitHubAP_AHRS: initialize yaw_deltat in AP_AHRS_DCM.cppGemini CLI
45baddf3 on GitHubAP_GPS: fix payload length check skip for when CFG VALSET message is beingGitHub 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	3,128
Merge commits removed	−0
CI / dependency bots removed	−3
Considered	3,125

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →C++ AI coding statisticsCompare evidence across C++ 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 ArduPilot/ardupilot

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	6.2%	385
2026-03	5.2%	404
2026-04	14.7%	348
2026-05	7.6%	383
2026-06	20.8%	327
2026-07	24.8%	471
2026-08	22.7%	493
2026-09	21.7%	314