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.

Settings management using pydantic

01Result

pydantic/pydantic-settings ↗

pydantic/pydantic-settings AI coding statistics: 67.8%

of 90 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 90 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

67.8% agent · top contributor 63.9%21 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

agent commits

other considered commits

agent contributors

63.9%

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

58assisted

3autonomous

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: 87.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	57	63.3%
GitHub Copilot	GitHub	9	10%
Cursor Agent	Anysphere	1	1.1%

03Evidence

Inspect the matches

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

Matched commit samples

ab1aaa7c on GitHubfix: slice the case-normalized prefix in dotenv match_prefix (#968)Claude Code
d357d7bf on GitHubReach 100% test coverage (#963)Claude Code
12cdb0a3 on GitHubfix: read JSON and YAML config as UTF-8, not the locale encoding (#955)Claude Code
55e9a4dc on GitHubAdd env_file_depth for parent directory env file lookup (#940)GitHub Copilot
e2f3d014 on GitHubdocs: clarify alias + nested model env lookup with populate_by_name (#933)GitHub Copilot
b7aa48aa on GitHubdocs: recommend async settings loading pattern (#908)GitHub Copilot
5eb72948 on GitHubAdd CliVariadicArg for named variadic CLI options (#949)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	125
Merge commits removed	−0
CI / dependency bots removed	−35
Considered	90

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 pydantic/pydantic-settings

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	61.5%	13
2026-03	81.8%	11
2026-04	55.6%	9
2026-05	40%	5
2026-06	54.5%	11
2026-07	87.5%	16
2026-08	70.6%	17
2026-09	62.5%	8