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.

A fast & densely stored hashmap and hashset

01Result

martinus/unordered_dense ↗

martinus/unordered_dense AI coding statistics: 96.9%

of 359 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

96.9% agent · top contributor 79.9%3 contributors

individual

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

348

agent commits

other considered commits

agent contributors

79.9%

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

348assisted

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: 98.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	348	96.9%

03Evidence

Inspect the matches

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

Matched commit samples

523ca3db on GitHubbench: measure the rehash pipeline below 200000 entries, where it never waClaude Code
1c8636e8 on GitHubrelease: 5.0.1Claude Code
7a8aad30 on GitHubindex: rename group_storage::slots, which Qt's macro eatsClaude Code

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	359
Merge commits removed	−0
CI / dependency bots removed	−0
Considered	359

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 →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 martinus/unordered_dense

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	1
2026-07	75%	12
2026-08	96.8%	93
2026-09	98.4%	253