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 trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。

WenyuChiou/awesome-agentic-ai-zh ↗

WenyuChiou/awesome-agentic-ai-zh AI coding statistics: 69.7%

of 651 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
69.7% agent · top contributor 92.7%4 contributors
individual

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

454
agent commits
197
other considered commits
4
agent contributors
92.7%
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

454assisted
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
2026-0580.2%399
2026-06100%40
2026-0774.4%39
2026-0841.8%153
2026-095%20

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic44468.2%
Gemini CLIGoogle71.1%
OpenAI CodexOpenAI40.6%
GitHub CopilotGitHub20.3%

Inspect the matches

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

Matched commit samples

  • e4d7790f on GitHubcontent(stage5): cut the opening wall and the stale Stack section (#132)Claude Code
  • ac1226fa on GitHubchore(release): backfill the 2026-08-23 CHANGELOG and bump to 2026.08.23 (Claude Code
  • bd100366 on GitHubcontent: cut nine restatements found by the readability audit (#126)Claude Code
  • 997516bd on GitHubdocs(R4+R5): mirror sync 4 stems × 2 locales (Gemini delegate + subagent aGemini CLI
  • 8ae18e69 on GitHubdocs(mirrors): sync Stage 3 mirror to refactored zh-TW canonical (Gemini dGemini CLI
  • 488526a9 on GitHubdocs(mirrors): sync Stage 4 mirror to refactored zh-TW canonical (Gemini dGemini CLI
  • 414db553 on GitHubdocs(R2): 默認→預設 sweep + jargon glosses (Codex×2 parallel, 4 drift rejectedOpenAI Codex
  • 706d2571 on GitHubfix(anchors): cleanup 37 legacy broken anchors + flip anchor-validator to OpenAI Codex
  • fe989bd8 on GitHubdocs(mirrors): sync Stage 1 pricing table (en + zh-Hans) via Codex delegatOpenAI Codex
  • c134a844 on GitHubdocs(readme): simplify animated banner links (#265)GitHub Copilot
  • 862e861e on GitHubcontent(stage0): restore honest resource ratings (#143)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 window704
Merge commits removed−28
CI / dependency bots removed−25
Considered651

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 WenyuChiou/awesome-agentic-ai-zh

Scan another repository