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.

Web vulnerability scanner written in Python3

01Result

wapiti-scanner/wapiti ↗

wapiti-scanner/wapiti AI coding statistics: 74.1%

of 112 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

74.1% agent · top contributor 47%3 contributors

individual

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

agent commits

other considered commits

agent contributors

47%

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

83assisted

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	58	51.8%
Cursor Agent	Anysphere	25	22.3%

03Evidence

Inspect the matches

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

Matched commit samples

ce7bb417 on GitHubfix(explorer): scope soft-404 detection to non-error, non-PATH_INFO responClaude Code
141fd24f on GitHubfix(explorer): detect soft-404 / SPA catch-all pages before persisting theClaude Code
3bef6f65 on GitHubbump version to 3.3.1, update changelogClaude Code
87696c2e on GitHubperf(persister): éviter les deepcopy inutiles lors de la sérialisationCursor Agent
50f1fc99 on GitHubRegroupement des transactions dans add_payload, save_request et save_requeCursor Agent
d1835ffe on GitHubCorrection du triple N+1 dans _get_paths()Cursor Agent

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	112
Merge commits removed	−0
CI / dependency bots removed	−0
Considered	112

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python 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 wapiti-scanner/wapiti

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	71.4%	35
2026-05	81.3%	32
2026-06	100%	1
2026-07	70.7%	41
2026-08	66.7%	3