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.

A Python utility / library to sort imports.

01Result

PyCQA/isort ↗

PyCQA/isort AI coding statistics: 19%

of 184 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

19% agent · top contributor 91.4%4 contributors

individual

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

agent commits

149

other considered commits

agent contributors

91.4%

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

3assisted

32autonomous

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: 40.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	33	17.9%
Claude Code	Anthropic	2	1.1%

03Evidence

Inspect the matches

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

Matched commit samples

131f4adc on GitHubFix review typing and import order in CLI invocation testGitHub Copilot
94919004 on GitHubTest python -m isort invocation directlyGitHub Copilot
f0a2dca3 on GitHubFix python -m isort by excluding __main__ from mypycGitHub Copilot
c2658001 on GitHubFix typo in _preconvert docstring: JSONifyiable -> JSONifiableClaude Code
fd2514b8 on GitHubFix unindented comments being corrupted in indented blocksClaude 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	322
Merge commits removed	−107
CI / dependency bots removed	−31
Considered	184

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 →Python AI coding statisticsCompare evidence across Python 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 PyCQA/isort

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	12.5%	8
2026-03	40.9%	66
2026-04	14.3%	7
2026-05	10.5%	19
2026-06	0%	10
2026-07	3%	33
2026-08	7.3%	41