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.

Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound insight commands.

01Result

mvanhorn/cli-printing-press ↗

mvanhorn/cli-printing-press AI coding statistics: 40.5%

of 1,887 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
40.5% agent · top contributor 55.6%46 contributors
team

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

765
agent commits
1,122
other considered commits
46
agent contributors
55.6%
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

765assisted
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
2026-0385.2%297
2026-0459%283
2026-0516.6%735
2026-0621.6%231
2026-0717.2%99
2026-0855.6%171
2026-0985.9%71

Peak month: 85.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic62533.1%
Cursor AgentAnysphere1437.6%
DevinCognition10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 79b74f2e on GitHubfix(cli): accept x-tenant-env-var/x-path-template-env-vars at doc root (#4Claude Code
  • 81d5a6b6 on GitHubfix(cli): extract items from map-keyed collections (#4335)Claude Code
  • 2880827b on GitHubfix(cli): send spec-declared query param defaults from sync (#4343)Claude Code
  • a09ce683 on GitHubfix(cli): rebuild FTS5 with trigram so CJK substrings match (#4690)Cursor Agent
  • 58675804 on GitHubfix(ci): raise generator shard timeout and cut speculative fan-out (#4710)Cursor Agent
  • 64bf7654 on GitHubfix(cli): skip typed non-zero dogfood exits (#4676)Cursor Agent
  • 7f6382d4 on GitHubfix(generator): emit toolchain floor and pin validate govulncheck to modulDevin

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 window1,974
Merge commits removed−38
CI / dependency bots removed−49
Considered1,887

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 →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/cli-printing-press

Scan another repository

Try