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.

Unified Schema-Based Information Extraction

01Result

fastino-ai/GLiNER2 ↗

fastino-ai/GLiNER2 AI coding statistics: 23.1%

of 78 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 78 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

23.1% agent · top contributor 44.4%3 contributors

individual

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

agent commits

other considered commits

agent contributors

44.4%

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

18assisted

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	13	16.7%
Cursor Agent	Anysphere	5	6.4%

03Evidence

Inspect the matches

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

Matched commit samples

c0bb42b3 on GitHubUse license file reference for broader setuptools compatibilityClaude Code
86239d4c on GitHubAdd missing license and metadata to pyproject.tomlClaude Code
7a5ab17a on GitHubAdd training-level integration tests for batch collation fixClaude Code
6234e37d on GitHubNarrow the classification pair decode; lock the training gold contractCursor Agent
022cfc67 on GitHubStop manufacturing true_label sentinels on the inference pathCursor Agent
7543d4b2 on GitHubDefer trainer/peft import until extract collation.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	119
Merge commits removed	−41
CI / dependency bots removed	−0
Considered	78

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 →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 fastino-ai/GLiNER2

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	40%	5
2026-03	33.3%	18
2026-04	29.4%	17
2026-05	0%	2
2026-06	0%	11
2026-07	0%	14
2026-08	0%	6
2026-09	100%	5