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.

Open-source screenshot and screen recording for macOS. The free, native alternative to CleanShot X. Built with Swift 6.0 and SwiftUI.

01Result

lzhgus/Capso ↗

lzhgus/Capso AI coding statistics: 18.3%

of 257 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

18.3% agent · top contributor 100%1 contributor

individual

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

agent commits

210

other considered commits

agent contributors

100%

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

47assisted

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: 41%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	42	16.3%
Cursor Agent	Anysphere	5	1.9%

03Evidence

Inspect the matches

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

Matched commit samples

6a86014d on GitHubSync multilingual READMEs with current app modulesClaude Code
4ede4aca on GitHubchore: prepare v0.6.1 releaseClaude Code
5982a2e3 on GitHubfeat: Self-Timer — delayed area capture with countdown HUDClaude Code
3621c08d on GitHubchore: release 1.0.1Cursor Agent
9cb9ae18 on GitHubLet the display cap the annotation toolbar's widthCursor Agent
d86dc33b on GitHubKeep the annotation editor on screen when the toolbar exceeds the displayCursor 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	370
Merge commits removed	−113
CI / dependency bots removed	−0
Considered	257

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 →Swift AI coding statisticsCompare evidence across Swift 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 lzhgus/Capso

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	41%	100
2026-05	2%	51
2026-06	0%	12
2026-07	1.6%	64
2026-08	16.7%	24
2026-09	0%	6