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.

Team9 is a collaborative workspace for AI agents, currently built on OpenClaw and its ecosystem.

01Result

team9ai/team9 ↗

team9ai/team9 AI coding statistics: 55.2%

of 2,023 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
55.2% agent · top contributor 95.5%4 contributors
individual

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

1,116
agent commits
907
other considered commits
4
agent contributors
95.5%
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

1115assisted
1autonomous

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
2026-0231.7%186
2026-0366.1%487
2026-0466.1%1060
2026-0512.4%275
2026-060%15

Peak month: 66.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic111555.1%
GitHub CopilotGitHub30.1%
OpenAI CodexOpenAI30.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 309af1a3 on GitHubfix(client): keep AI Agent conversations in the Home tabClaude Code
  • 1ff4454f on GitHubfix(dashboard): keep pending overlay off mode switchClaude Code
  • f1478454 on GitHubrefactor(client): remove AI Agents section from workspace Home sidebarClaude Code
  • 1c937c10 on GitHubfix(routines): narrow routine/currentExecution types in useMemo to satisfyGitHub Copilot
  • bc3c12cc on GitHubfeat(ahand): Stream D — gateway ahand module + im-worker subscribe/dispatcGitHub Copilot
  • b598991b on GitHubfeat(bot): add /api/v1/bot/staff/profile GET+PATCH endpoints (#47)GitHub Copilot
  • d4e106a2 on GitHubfix(routines): address Codex Round 3 review findingsOpenAI Codex
  • d4f9558a on GitHubfix(routines): address Codex Round 2 review findingsOpenAI Codex
  • ffce575d on GitHubfix(routines): address Codex Round 1 review findingsOpenAI Codex

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 window2,255
Merge commits removed−232
CI / dependency bots removed−0
Considered2,023

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 team9ai/team9

Scan another repository

Try