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.

01Result

turnstonelabs/turnstone ↗

turnstonelabs/turnstone AI coding statistics: 1.5%

of 1,754 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.5% agent · top contributor 63%5 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

27
agent commits
1,727
other considered commits
5
agent contributors
63%
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

26assisted
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
2026-030%356
2026-040.7%270
2026-050%292
2026-066.3%334
2026-070.3%352
2026-083.3%92
2026-090%58

Peak month: 6.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic181%
GitHub CopilotGitHub90.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • 73fb84b4 on GitHubfix(helm): make the Kubernetes chart installable and multi-node capable (#Claude Code
  • e7e3135a on GitHubdocs(hypothesis): add "Appendix: model implementation" — cancellation as tClaude Code
  • d1acded0 on GitHubdocs(hypothesis): round-sixteen (maxima re-run) — semantic-axis fixes the Claude Code
  • d2a6c285 on GitHubStabilize context-overflow compaction test in Python 3.11 CI (#1006)GitHub Copilot
  • 0cdb6798 on GitHubFollow-ups on the #832 fold: supersession predicate, wire-prep error hygieGitHub Copilot
  • 217d3a3a on GitHubfeat(mcp): autonomous reconnect + liveness for static MCP servers (#768)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 window1,922
Merge commits removed−12
CI / dependency bots removed−156
Considered1,754

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 →Python AI coding statisticsCompare evidence across Python 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 turnstonelabs/turnstone

Scan another repository

Try