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.

A catgirl who lives with you in real time — reaching out first, sharing your media, and actually getting things done, powered by an embodied emotional engine.🐱❤️一只会主动找你玩的 AI 猫娘。

Project-N-E-K-O/N.E.K.O ↗

Project-N-E-K-O/N.E.K.O AI coding statistics: 42.2%

of 2,590 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
42.2% agent · top contributor 58.7%38 contributors
team

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

1,094
agent commits
1,496
other considered commits
38
agent contributors
58.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

1094assisted
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
2026-0210.8%167
2026-0321.8%225
2026-0458.8%466
2026-0557.5%478
2026-0642.2%476
2026-0729.4%412
2026-0841.3%281
2026-0947.1%85

Peak month: 58.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic106941.3%
Cursor AgentAnysphere271%
OpenAI CodexOpenAI30.1%
GitHub CopilotGitHub30.1%

Inspect the matches

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

Matched commit samples

  • bf65bef5 on GitHubfix(watch-together): Electron 下 /一起看 打不开窗口;陪看期间插件播报几乎不出声 (#3125)Claude Code
  • 74a175c3 on GitHubfix(minigames): integrate shared character, avatar and image services (#31Claude Code
  • 33f3c1e0 on GitHubfeat(watch-together): 看视频期间见缝插针播报插件回应,自动连播每段加小结与回复 (#3121)Claude Code
  • c174ad15 on GitHubchore(config): 把 OpenAI/GLM/Kimi/硅基默认模型对齐到当前可用版本Cursor Agent
  • f9b18402 on GitHubfeat(card-drop): hand Desktop OAuth session to community via one-time natiCursor Agent
  • 76e02179 on GitHubfix(plugin): 插件化 Testbench 时暴露的宿主 / SDK 缺陷修复(testbench_dist 已移出本体) (#2953)Cursor Agent
  • f0ed4c07 on GitHub[codex] docs: add Linux desktop runtime triage guide (#1708)OpenAI Codex
  • c49d6fe8 on GitHubIntegrate SoccerDemo with routed character interaction (#1110)OpenAI Codex
  • 9ecbd79b on GitHub[codex] fix Live2D motion cleanup residuals (#1061)OpenAI Codex
  • e24c899b on GitHubAdd new SVG icons for sharing, image, and import functionalities (#672)GitHub Copilot
  • 8bd11227 on GitHubFeature/voice proactive chat (#614)GitHub Copilot
  • abc23ccb on GitHubfeat: integrate OpenFang as headless agent execution backend (#557)GitHub Copilot

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 window2,605
Merge commits removed−15
CI / dependency bots removed−0
Considered2,590

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 Project-N-E-K-O/N.E.K.O

Scan another repository