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.

Command line driven CI frontend and development task automation tool.

01Result

tox-dev/tox ↗

tox-dev/tox AI coding statistics: 5.5%

of 307 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.5% agent · top contributor 41.2%7 contributors
team

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

17
agent commits
290
other considered commits
7
agent contributors
41.2%
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

16assisted
1autonomous

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
2026-027.2%153
2026-034.4%45
2026-0414.3%7
2026-050%11
2026-060%13
2026-0710%30
2026-080%38
2026-090%10

Peak month: 14.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic175.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • e19069f6 on GitHubDo not let a lone quote in a set_env value swallow the marker (#3988)Claude Code
  • a1f76cfc on GitHubRun sequentially for run-parallel -p 0 instead of at CPU count (#3989)Claude Code
  • eaf7b51f on GitHub✨ feat(python): match free-threaded and debug interpreter builds (#3986)Claude 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 window358
Merge commits removed−0
CI / dependency bots removed−51
Considered307

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 tox-dev/tox

Scan another repository

Try