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.

A general purpose HTTP reverse proxy and forwarding tool. Now written in Go!

01Result

tobychui/zoraxy ↗

tobychui/zoraxy AI coding statistics: 12%

of 184 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12% agent · top contributor 27.3%9 contributors
org-wide

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

22
agent commits
162
other considered commits
9
agent contributors
27.3%
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

18assisted
4autonomous

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
2026-020%19
2026-036.7%15
2026-046.7%15
2026-052.8%36
2026-0631.3%32
2026-0724.2%33
2026-084.2%24
2026-090%10

Peak month: 31.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic116%
GitHub CopilotGitHub73.8%
Cursor AgentAnysphere42.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • af0741cb on GitHubFix: restore per-request TLS SNI for IP-addressed HTTPS upstreamsClaude Code
  • f73ddfd8 on GitHubfeat(forward-auth): bulk apply/remove the auth callback vdir by Forward AuClaude Code
  • 0ec8098d on GitHubstyle(pluginmanager): trim accordion scoping comment in plugins.htmlClaude Code
  • 578255af on GitHubApply remaining changesGitHub Copilot
  • bd16ea63 on GitHubFix test failures: dpcore URL encoding, eventsystem JSON, dbleveldb write/GitHub Copilot
  • 4d7fa98c on GitHubSync example plugin events.go files with source (add TrustProxyHeadersOnlyGitHub Copilot
  • f54f1316 on GitHubfix(ui): detach rate-limit handlers before loading shared modal valueCursor Agent
  • 4af33aac on GitHubfix(zorxauth): honor request scheme for SSO URL normalizationCursor Agent
  • 72bf1d7d on GitHubFix SSO redirect loop when SSO URL omits http(s) schemeCursor Agent

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 window282
Merge commits removed−80
CI / dependency bots removed−18
Considered184

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →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 tobychui/zoraxy

Scan another repository

Try