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.

The Domain-Correct Quantities and Units Library for C++ — full quantity kind safety, ISO 80000 compliant, C++29 standardization candidate.

01Result

mpusz/mp-units ↗

mpusz/mp-units AI coding statistics: 34.8%

of 601 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

34.8% agent · top contributor 99%3 contributors

individual

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

209

agent commits

392

other considered commits

agent contributors

99%

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

209assisted

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: 86.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	188	31.3%
GitHub Copilot	GitHub	21	3.5%

03Evidence

Inspect the matches

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

Matched commit samples

f082a278 on GitHubci: clang 23 added to the build matrixClaude Code
ad542b54 on GitHubdocs: the import-std snippet silences the warning now, not just its errorClaude Code
056fb92e on GitHubfix(devcontainer): setup_compilers.sh is now safe to re-runClaude Code
423db353 on GitHubfeat(example): currency example improvedGitHub Copilot
e73cef31 on GitHubstyle: pre-commitGitHub Copilot
477b8eb7 on GitHubdocs: marking of subkinds in hierarchies changed to subgraphsGitHub 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	627
Merge commits removed	−23
CI / dependency bots removed	−3
Considered	601

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 →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 mpusz/mp-units

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	88
2026-03	0%	98
2026-04	21.6%	97
2026-05	19.7%	76
2026-06	52.9%	70
2026-07	73.9%	69
2026-08	86.4%	66
2026-09	75.7%	37