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 AI browser agent for Chrome and Firefox (monorepo) 🧠

01Result

webbrain-one/webbrain ↗

webbrain-one/webbrain AI coding statistics: 16.4%

of 3,778 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

16.4% agent · top contributor 79.3%15 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

619

agent commits

3,159

other considered commits

agent contributors

79.3%

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

610assisted

9autonomous

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: 56.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	488	12.9%
Cursor Agent	Anysphere	71	1.9%
GitHub Copilot	GitHub	59	1.6%
OpenAI Codex	OpenAI	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

8197fe96 on GitHubfix(agent): verify GIF subtype and read singular articles as exact countsClaude Code
7b63a68e on GitHubfix(agent): read reply commands as publication intentClaude Code
2b1f7b4a on GitHubrefactor(agent): hoist attachment-parsing regexes to module scopeClaude Code
5bb5a2a5 on GitHubRefresh form inventories after value mutations in workflow tests.Cursor Agent
e592953b on GitHubStale form inventories after successful value-driven mutations.Cursor Agent
bf1ab229 on GitHubResolve Gmail inline-reply recipients from the enclosing reply container.Cursor Agent
3db17d30 on GitHubHarden Ask-to-Act handoff classificationGitHub Copilot
b7a02e19 on GitHubFix Ask-to-Act handoff lifecycleGitHub Copilot
db5130e6 on GitHubBound Ask-to-Act classifier and retry payloadsGitHub Copilot
04bb664b on GitHubfix(anthropic): yield done when replay fails mid-stream instead of throwinOpenAI Codex

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	5,510
Merge commits removed	−1,341
CI / dependency bots removed	−391
Considered	3,778

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 webbrain-one/webbrain

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	37.3%	153
2026-05	56.7%	363
2026-06	11.4%	507
2026-07	5.9%	1177
2026-08	14.4%	1131
2026-09	14.8%	447