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.

Portable DNS resolver in Rust — .numa local domains, ad blocking, developer overrides

01Result

razvandimescu/numa ↗

razvandimescu/numa AI coding statistics: 29.5%

of 529 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
29.5% agent · top contributor 98.7%2 contributors
individual

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

156
agent commits
373
other considered commits
2
agent contributors
98.7%
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

156assisted
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
2026-0393.1%102
2026-0427.9%219
2026-050%106
2026-060%43
2026-070%15
2026-080%28
2026-090%16

Peak month: 93.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic15629.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • 289f2b97 on GitHubchore: remove built blog HTML from tracking (built by CI)Claude Code
  • fb4cbe0b on GitHubchore: update DoT blog post — mark DoH server as shipped in v0.12.0Claude Code
  • 156b68de on GitHubfix: replace unscannable QR art with placeholder in blog post (#80)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 window686
Merge commits removed−120
CI / dependency bots removed−37
Considered529

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 →Rust AI coding statisticsCompare evidence across Rust 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 razvandimescu/numa

Scan another repository

Try