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.

Share coding agents with your team on phone and desktop

01Result

LodyAI/Lody ↗

LodyAI/Lody AI coding statistics: 18.9%

of 509 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
18.9% agent · top contributor 49%15 contributors
org-wide

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

96
agent commits
413
other considered commits
15
agent contributors
49%
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

49assisted
47autonomous

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
2026-0814.4%284
2026-0924.4%225

Peak month: 24.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic8115.9%
Cursor AgentAnysphere132.6%
GitHub CopilotGitHub20.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 696e68fd on GitHubfix(electron): draw the context menu Electron does not shipClaude Code
  • 7249efeb on GitHubfix(components): keep a dropdown submenu off the screen edge and off its pClaude Code
  • 6da20a90 on GitHubfeat(components): one fixed template for the conversation share card (#697Claude Code
  • c70c3c73 on GitHubdocs(site-docs): share link vs live handoff compare pageCursor Agent
  • ac07385d on GitHubfix(site-docs): improve mobile LCP/INP by cutting first-screen JS (#444)Cursor Agent
  • d109b6de on GitHubchore(site-docs): GEO answer blocks, FAQ JSON-LD, internal links (#391)Cursor Agent
  • e42f786a on GitHubfix(components): isolate desktop window sync caches (#641)GitHub Copilot
  • 24077862 on GitHubtest(e2e): add desktop verification lanes (#372)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 window746
Merge commits removed−63
CI / dependency bots removed−174
Considered509

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 LodyAI/Lody

Scan another repository

Try