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.

Agentic review of Linux Kernel code changes

01Result

sashiko-dev/sashiko ↗

sashiko-dev/sashiko AI coding statistics: 3.5%

of 1,288 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

3.5% agent · top contributor 40%6 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

agent commits

1,243

other considered commits

agent contributors

40%

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

45assisted

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: 9.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	32	2.5%
Gemini CLI	Google	13	1%

03Evidence

Inspect the matches

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

Matched commit samples

f74a57a2 on GitHubdocs: add vLLM provider documentation and examplesClaude Code
9d9ad5da on GitHubAdd support for vLLM providerClaude Code
153b96d8 on GitHubai: add kiro-cli providerClaude Code
ecb1ef44 on GitHubindex.html: add theme toggling, colorblind mode and settings menuGemini CLI
2b0be444 on GitHubai/claude: unify JSON formatting enforcement via system promptsGemini CLI
bbd583be on GitHubai/claude_cli: improve error classification and response formattingGemini CLI

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	1,380
Merge commits removed	−19
CI / dependency bots removed	−73
Considered	1,288

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →Rust AI coding statisticsCompare evidence across Rust 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 sashiko-dev/sashiko

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	277
2026-03	4.1%	123
2026-04	9.3%	151
2026-05	8.2%	219
2026-06	6.5%	92
2026-07	0%	74
2026-08	1.6%	124
2026-09	0%	228