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.

Self-hosted MCP gateway and control plane for connecting, controlling, and operating MCP servers.

01Result

samanhappy/mcphub ↗

samanhappy/mcphub AI coding statistics: 32%

of 278 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
32% agent · top contributor 47.2%12 contributors
org-wide

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

89
agent commits
189
other considered commits
12
agent contributors
47.2%
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

89assisted
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
2026-020%10
2026-0323.3%30
2026-0423.1%26
2026-0556.3%48
2026-0657.1%42
2026-0727.3%22
2026-0815.8%57
2026-0923.3%43

Peak month: 57.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic4917.6%
GitHub CopilotGitHub3211.5%
Gemini CLIGoogle124.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • b6887ef1 on GitHubfix(build): keep shell scripts at LF so Windows checkouts build a working Claude Code
  • 895f448c on GitHubfix(cache): scope the npx reinstall to the server being reinstalled (#1182Claude Code
  • a55a6509 on GitHubfeat(mcp): allow bounding how many servers connect at once on startup (#11Claude Code
  • 1772c7af on GitHubfeat: add visibility controls for groups (#1175)GitHub Copilot
  • b941d4dc on GitHubfix: reconnect upstream OAuth servers after reauthorization (#1128)GitHub Copilot
  • 0e8fed09 on GitHubRemove vector embeddings under old name when renaming a server (#1041)GitHub Copilot
  • d74d1bef on GitHubfeat: per-session upstream client isolation for stateful MCP servers (#985Gemini CLI
  • 349f8b73 on GitHubfix: preserve in-flight OAuth state on full reload (#981)Gemini CLI
  • be40426b on GitHubfeat: enhance session management with improved transport rehydration and eGemini CLI

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 window361
Merge commits removed−0
CI / dependency bots removed−83
Considered278

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 samanhappy/mcphub

Scan another repository

Try