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.

runs anywhere. uses anything

01Result

Twigpine/openclaude ↗

Twigpine/openclaude AI coding statistics: 10.7%

of 1,065 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
10.7% agent · top contributor 19.3%44 contributors
org-wide

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

114
agent commits
951
other considered commits
44
agent contributors
19.3%
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

111assisted
3autonomous

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
2026-0340%5
2026-0416.9%408
2026-058.1%148
2026-066.8%264
2026-074.7%169
2026-087%57
2026-097.1%14

Peak month: 40%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic948.8%
GitHub CopilotGitHub151.4%
Cursor AgentAnysphere40.4%
Other / generic agentVarious10.1%
DevinCognition10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 31ac8a6e on GitHubperf: stop busting the prompt cache and slim per-turn context (#2142)Claude Code
  • 645d596e on GitHubfix(code-reviewer): require inline diff input and preserve read-only searcClaude Code
  • 787f2a93 on GitHubrefactor(cli): commander-authoritative argv handling for SSH / cc:// and rClaude Code
  • 2e687df4 on GitHubfix(image): allow large/metadata-less screenshots through on resize failurGitHub Copilot
  • c461a036 on GitHubfeat: merge knowledge graph + conversation arc into memdir (#1811)GitHub Copilot
  • 5b1c5a2c on GitHubMention Arch AUR (#1286)GitHub Copilot
  • 10a9190b on GitHubfix(ui): keep SpinnerModeGlyph visible inside status parens (#2047)Cursor Agent
  • 1bd273d4 on GitHubfix: isolate OpenClaude config from Claude Code (#1875)Cursor Agent
  • 70b4b079 on GitHubfix(repl): show permission prompts while draft input is present (#1393)Cursor Agent
  • aa936cda on GitHubCentralize credential redaction in src/utils/redaction.ts + channel gate tOther / generic agent
  • 90360d3e on GitHubfix(stdin,mcp): guard rawModeEnabledCount and defer MCP connections to preDevin

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 window1,209
Merge commits removed−103
CI / dependency bots removed−41
Considered1,065

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 →Devin commitsBrowse repositories with detected Devin 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 Twigpine/openclaude

Scan another repository

Try