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 headless Chrome/Chromium driver on top of Puppeteer. Take screenshots, generate PDFs, extract text and HTML with a production-ready API.

01Result

microlinkhq/browserless ↗

microlinkhq/browserless AI coding statistics: 28.8%

of 281 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

28.8% agent · top contributor 90.1%4 contributors

individual

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

agent commits

200

other considered commits

agent contributors

90.1%

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

74assisted

7autonomous

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: 51.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	50	17.8%
Cursor Agent	Anysphere	38	13.5%

03Evidence

Inspect the matches

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

Matched commit samples

9670a9a1 on GitHubfix(goto): deny notifications by default (#931)Claude Code
784b7b59 on GitHubfix(goto): dismiss notification opt-in overlays (#933)Claude Code
ece0f276 on GitHubfix(devices): derive the default desktop identity from the host OS (#932)Claude Code
b8961951 on GitHubfix(errors): treat Connection closed as context reset (#934)Cursor Agent
615406e6 on GitHubfix(devices): sync Chrome UA with Puppeteer (#918)Cursor Agent
5316dd4a on GitHubfix: move --sequential after pnpm runCursor 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	357
Merge commits removed	−0
CI / dependency bots removed	−76
Considered	281

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 →JavaScript AI coding statisticsCompare evidence across JavaScript 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 microlinkhq/browserless

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	37
2026-03	0%	33
2026-04	0%	12
2026-05	21.4%	42
2026-06	38%	50
2026-07	50%	28
2026-08	51.2%	43
2026-09	47.2%	36