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.

Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed.

01Result

mvanhorn/printing-press-library ↗

mvanhorn/printing-press-library AI coding statistics: 25.4%

of 2,116 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
25.4% agent · top contributor 32.2%102 contributors
org-wide

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

538
agent commits
1,578
other considered commits
102
agent contributors
32.2%
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

538assisted
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
2026-0377.8%9
2026-0445.3%212
2026-0521.9%602
2026-0618.1%608
2026-0721%291
2026-0832.1%302
2026-0938%92

Peak month: 77.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic46321.9%
Cursor AgentAnysphere653.1%
OpenAI CodexOpenAI200.9%
DevinCognition10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 96526ef8 on GitHubfeat(immoweb): add immoweb (#1995)Claude Code
  • 708f5c5e on GitHubfix(peloton): response bloat, resumable pagination, and sync warning visibClaude Code
  • 1034d6f7 on GitHubfix(peloton): workflow status --json/--agent returns a structured envelopeClaude Code
  • c56a8ba1 on GitHubfeat(swiggy): leftover from #1993 — Greptile P1 fixes (#1994)Cursor Agent
  • a1b42a71 on GitHubfix(kvmctl): leftover from #1965 — rearm_otg read_only (#1972)Cursor Agent
  • 5701d1ea on GitHubfix(substack): leftover from #1567 — reader subscriptions list (#1958)Cursor Agent
  • 51a1a9da on GitHubdocs(library): canonicalize README install block (npx defaults, agent listOpenAI Codex
  • cd90d20c on GitHubfix(ci): cancel-in-progress=false so cancelled check_runs don't pile up (#OpenAI Codex
  • 9ad773bf on GitHubfix(ci): conversation-resolution check race + duplicate check_run (#623)OpenAI Codex
  • f505cabe on GitHubchore(library): drop verbose manuscript proof logs and ignore future onesDevin

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 window3,662
Merge commits removed−199
CI / dependency bots removed−1,347
Considered2,116

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 →Devin commitsBrowse repositories with detected Devin signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Go AI coding statisticsCompare evidence across Go 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 mvanhorn/printing-press-library

Scan another repository

Try