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.

Install your own AmneziaWG 3.1 VPN server on a fresh Ubuntu or Debian VPS with one command. Made for networks that block WireGuard. No Docker, QR-code import, 2.0 on request for routers.

bivlked/amneziawg-installer ↗

bivlked/amneziawg-installer AI coding statistics: 33%

of 361 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
33% agent · top contributor 99.2%2 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

119
agent commits
242
other considered commits
2
agent contributors
99.2%
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

119assisted
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
2026-0395.2%125
2026-040%82
2026-050%27
2026-060%31
2026-070%36
2026-080%40
2026-090%20

Peak month: 95.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic11933%

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 window390
Merge commits removed−18
CI / dependency bots removed−11
Considered361

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 bivlked/amneziawg-installer

Scan another repository