Pulse
2026-09-18-v3.0
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.

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)

01Result

urchade/GLiNER ↗

urchade/GLiNER AI coding statistics: 17.4%

of 132 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
17.4% agent · top contributor 91.3%2 contributors
individual

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

23
agent commits
109
other considered commits
2
agent contributors
91.3%
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

23assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0250%6
2026-0339.1%23
2026-0424.3%37
2026-050%7
2026-060%10
2026-079.1%22
2026-080%4
2026-090%23

Peak month: 50%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic2317.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 02c4ca4a on GitHubfix: clean up model.py import duplication, restore lost docstring, fix rufClaude Code
  • 016cd42f on GitHubfix: use is_module_available consistently, move ablation scriptsClaude Code
  • 6513398d on GitHubFall back when assign-load leaves meta parametersClaude 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 window183
Merge commits removed−51
CI / dependency bots removed−0
Considered132

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 →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 urchade/GLiNER

Scan another repository

Try