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.

DuckLake is an integrated data lake and catalog format

01Result

duckdb/ducklake ↗

duckdb/ducklake AI coding statistics: 2.4%

of 1,075 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

2.4% agent · top contributor 23.1%11 contributors

org-wide

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

agent commits

1,049

other considered commits

agent contributors

23.1%

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

26assisted

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	26	2.4%

03Evidence

Inspect the matches

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

Matched commit samples

7b704fc4 on GitHubFix mc entrypoint being mangled by YAML foldingClaude Code
3f2e5096 on GitHubPull the MinIO images from quay.io so the MinIO CI job can startClaude Code
9a64ff2a on GitHubtest: drop redundant require-env DUCKLAKE_CI from scoped-attach testClaude 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	1,458
Merge commits removed	−383
CI / dependency bots removed	−0
Considered	1,075

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 →C++ AI coding statisticsCompare evidence across C++ 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 duckdb/ducklake

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	193
2026-03	2.2%	134
2026-04	2%	200
2026-05	3.5%	170
2026-06	1.6%	129
2026-07	7.1%	84
2026-08	3.2%	95
2026-09	2.9%	70