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.

Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.

01Result

54yyyu/zotero-mcp ↗

54yyyu/zotero-mcp AI coding statistics: 70.8%

of 455 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
70.8% agent · top contributor 41%33 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

322
agent commits
133
other considered commits
33
agent contributors
41%
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

322assisted
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
2026-0223.5%17
2026-0393.3%60
2026-0461.5%39
2026-0531.8%44
2026-0656.5%46
2026-0771.7%53
2026-0889%109
2026-0972.4%87

Peak month: 93.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic32270.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7b94f823 on GitHubchore: move experiments/ and vision/ off mainClaude Code
  • ee4ef007 on GitHubdocs: slim the README; move details to docs/ and add a guide for AI agentsClaude Code
  • a9092ce0 on GitHubrefactor: open PDFs once, read local files in place, sharpen layout detectClaude 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 window629
Merge commits removed−174
CI / dependency bots removed−0
Considered455

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 54yyyu/zotero-mcp

Scan another repository

Try