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.

ESP32 display that shows you your Claude Code usage

HermannBjorgvin/Clawdmeter ↗

HermannBjorgvin/Clawdmeter AI coding statistics: 47%

of 166 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
47% agent · top contributor 30.8%23 contributors
org-wide

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

78
agent commits
88
other considered commits
23
agent contributors
30.8%
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

78assisted
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
2026-04100%4
2026-0516.7%84
2026-0691.1%45
2026-0747.4%19
2026-0863.6%11
2026-09100%3

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7746.4%
GitHub CopilotGitHub10.6%

Inspect the matches

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

Matched commit samples

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 window224
Merge commits removed−58
CI / dependency bots removed−0
Considered166

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 HermannBjorgvin/Clawdmeter

Scan another repository