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 factory for one-shot engineering

01Result

superplanehq/superplane ↗

superplanehq/superplane AI coding statistics: 29.4%

of 1,873 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

29.4% agent · top contributor 28.1%30 contributors

org-wide

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

551

agent commits

1,322

other considered commits

agent contributors

28.1%

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

488assisted

63autonomous

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: 74.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	518	27.7%
Claude Code	Anthropic	34	1.8%

03Evidence

Inspect the matches

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

Matched commit samples

e42a8452 on GitHubfeat: Refresh backlog from intake sources (#7403)Cursor Agent
24d097ab on GitHubfeat: Show Polar webhook retry status (#7454)Cursor Agent
ceec5874 on GitHubfeat: Attach model picker to Start (#7477)Cursor Agent
a39b5c42 on GitHubfix: Clone notes on the canvas (#6250)Claude Code
bceeef8e on GitHubfix: Scheduler: first run skips current hour when minute has not passed yeClaude Code
bf195cc6 on GitHubfix: Relatively long commit message overflows in the commit message input Claude 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	2,061
Merge commits removed	−0
CI / dependency bots removed	−188
Considered	1,873

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 →Go AI coding statisticsCompare evidence across Go 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 superplanehq/superplane

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	8%	212
2026-03	18.6%	258
2026-04	11.6%	276
2026-05	19.5%	210
2026-06	26.3%	304
2026-07	27.1%	255
2026-08	73%	185
2026-09	74.6%	173