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.

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

01Result

lemonade-sdk/lemonade ↗

lemonade-sdk/lemonade AI coding statistics: 30.8%

of 1,022 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
30.8% agent · top contributor 42.2%41 contributors
org-wide

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

315
agent commits
707
other considered commits
41
agent contributors
42.2%
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

312assisted
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
2026-0215.4%123
2026-0323.4%137
2026-0437.4%91
2026-0529.1%110
2026-0637.8%188
2026-0730.6%144
2026-0834.2%184
2026-0944.4%45

Peak month: 44.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic29028.4%
GitHub CopilotGitHub353.4%
Cursor AgentAnysphere20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • e71baf23 on GitHubMoved the snap release candidate trigger from the repo-manager workflow (#Claude Code
  • 2897f245 on GitHubtools/version.py: fall back to a dated placeholder outside a git work treeClaude Code
  • 6e2b5bd3 on GitHubdocs(website): keep release candidates out of the homepage carousel (#3588Claude Code
  • 6a607106 on GitHubFix incompatible GGUF results in model search (#3198)GitHub Copilot
  • b45a6ce9 on GitHubci: retry apt-get on transient arm64 mirror 404s (#3353)GitHub Copilot
  • 505d7727 on GitHubFail startup when one resolved address cannot bind (#3197)GitHub Copilot
  • 319b0cd4 on GitHubfeat(cli): add --json output to lemonade cloud list (#3261)Cursor Agent
  • 059e001a on GitHubAdding support in backend and frontend UI for super-resolution (Real-ESRGACursor Agent

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 window1,051
Merge commits removed−8
CI / dependency bots removed−21
Considered1,022

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 →C++ AI coding statisticsCompare evidence across C++ 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 lemonade-sdk/lemonade

Scan another repository

Try