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.

Node.js port of Multi-user SocialCalc

01Result

audreyt/ethercalc ↗

audreyt/ethercalc AI coding statistics: 30.3%

of 488 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

30.3% agent · top contributor 94.6%2 contributors

individual

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

148

agent commits

340

other considered commits

agent contributors

94.6%

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

148assisted

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	148	30.3%

03Evidence

Inspect the matches

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

Matched commit samples

51ec72db on GitHubtest(e2e): real single-sheet smoke (was a test.skip placeholder)Claude Code
cf0192be on GitHubtest(oracle): widen equivalence suite by 16 scenariosClaude Code
4e7faf66 on GitHubfeat(worker): import xlsx/ods on POST /_/:room instead of 501Claude Code

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	523
Merge commits removed	−35
CI / dependency bots removed	−0
Considered	488

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 →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 audreyt/ethercalc

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	100%	1
2026-04	77.6%	165
2026-05	100%	3
2026-06	23.5%	68
2026-07	0%	110
2026-08	0%	140
2026-09	0%	1