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.

TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

01Result

nrslib/takt ↗

nrslib/takt AI coding statistics: 1.2%

of 1,430 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.2% agent · top contributor 35.3%9 contributors
org-wide

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

17
agent commits
1,413
other considered commits
9
agent contributors
35.3%
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

17assisted
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
2026-020.6%491
2026-032.6%155
2026-045%119
2026-052.8%71
2026-061%100
2026-070%165
2026-080.3%306
2026-090%23

Peak month: 5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic161.1%
Cursor AgentAnysphere10.1%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 81e5a2cf on GitHubfeat(observability): add opt-in OpenTelemetry spans, session logs, and metClaude Code
  • de7e021c on GitHubfix: detect claude-terminal prompt with v2.1 placeholder hint (#766)Claude Code
  • d62c1955 on GitHub[#695] feat(team-leader): PromptBasedStructuredCaller の JSON パース失敗時にリトライするClaude Code
  • f9acf819 on GitHubfix(pi): prefer user/project npm extensions over temporary install (#1423)Cursor Agent
  • 39537921 on GitHubfeat: スラッシュコマンドの補完メニューを実装 (#580)GitHub Copilot

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 window1,619
Merge commits removed−188
CI / dependency bots removed−1
Considered1,430

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 →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 nrslib/takt

Scan another repository

Try