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.

Build production-ready applications in TypeScript

01Result

Effect-TS/effect ↗

Effect-TS/effect AI coding statistics: 3.6%

of 2,266 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

3.6% agent · top contributor 49.4%27 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

agent commits

2,185

other considered commits

agent contributors

49.4%

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

81assisted

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: 6.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	79	3.5%
Cursor Agent	Anysphere	2	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

39933405 on GitHubFix Vitest timeout finalizer ordering (#8154)Claude Code
6e3ae7b6 on GitHubfix(ai): keep non-object tool results out of structuredContent (#7495)Claude Code
a5f78d3f on GitHubImplement schema-aware RPC serialization (#7387)Claude Code
5f217683 on GitHubRefactor arbitrary generation (#2348)Cursor Agent
4255c9ba on GitHubfix(HttpApi): strip space delimiter when decoding bearer/http credentials 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	2,297
Merge commits removed	−3
CI / dependency bots removed	−28
Considered	2,266

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 Effect-TS/effect

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	4.1%	366
2026-03	0.3%	293
2026-04	2.3%	132
2026-05	5.8%	120
2026-06	4.3%	139
2026-07	6.3%	332
2026-08	5.2%	519
2026-09	0.3%	365