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.

Which is the fastest web framework?

01Result

the-benchmarker/web-frameworks ↗

the-benchmarker/web-frameworks AI coding statistics: 3.3%

of 570 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

3.3% agent · top contributor 31.6%7 contributors

team

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

agent commits

551

other considered commits

agent contributors

31.6%

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

13assisted

6autonomous

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: 7.1%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	11	1.9%
GitHub Copilot	GitHub	6	1.1%
OpenAI Codex	OpenAI	1	0.2%
Cursor Agent	Anysphere	1	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

67d90d28 on GitHubRestore closed-loop zrk, size the generator, and pin morojs workers to theClaude Code
e619eec3 on GitHubAdd peregrine, as a raw ASGI/WSGI server and under FastAPI and DjangoClaude Code
573c3a1f on GitHubPin V's vc bootstrap so the toolchain build stops driftingClaude Code
3db29ccc on GitHubfix: include env file in sunrise-router-roadrunner road-runner imageGitHub Copilot
4ba4e2af on GitHubInitial planGitHub Copilot
bbcd9e9a on GitHubInitial planGitHub Copilot
d905488c on GitHubfeat(javascript): add Next.js benchmarkOpenAI Codex
7bcc1cac on GitHubUpdate @morojs/moro dependency versionCursor 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	1,900
Merge commits removed	−781
CI / dependency bots removed	−549
Considered	570

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 →PHP AI coding statisticsCompare evidence across PHP 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 the-benchmarker/web-frameworks

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	6.5%	92
2026-03	0%	133
2026-04	0%	32
2026-05	0%	73
2026-06	7.1%	56
2026-07	2.4%	42
2026-08	5.4%	92
2026-09	6%	50