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.

🐳 Matrix (An open network for secure, decentralized communication) server setup using Ansible and Docker

01Result

spantaleev/matrix-docker-ansible-deploy ↗

spantaleev/matrix-docker-ansible-deploy AI coding statistics: 48.2%

of 650 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

48.2% agent · top contributor 98.1%5 contributors

individual

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

313

agent commits

337

other considered commits

agent contributors

98.1%

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

310assisted

3autonomous

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: 77.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	310	47.7%
GitHub Copilot	GitHub	3	0.5%

03Evidence

Inspect the matches

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

Matched commit samples

f6ce1206 on GitHubStop running Dependabot alongside RenovateClaude Code
6cc5de4f on GitHubRun the i18n workflow when the i18n workflow itself changesClaude Code
5e9a20a3 on GitHubCorrect what the baibot OpenAI API key comment claimsClaude Code
a809f4d1 on GitHubChanges before error encounteredGitHub Copilot
ceebf644 on GitHubMake exim-relay benefits section more conciseGitHub Copilot
123dbbf1 on GitHubAdd "Why use exim-relay?" section to email documentationGitHub 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	1,186
Merge commits removed	−9
CI / dependency bots removed	−527
Considered	650

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 spantaleev/matrix-docker-ansible-deploy

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	26.4%	121
2026-03	11.9%	84
2026-04	10.3%	29
2026-05	77.9%	95
2026-06	66.7%	42
2026-07	75.6%	131
2026-08	46.5%	144
2026-09	0%	4