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.

Muesli: agent-native local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)

01Result

Muesli-HQ/muesli ↗

Muesli-HQ/muesli AI coding statistics: 16.9%

of 1,393 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
16.9% agent · top contributor 55.1%18 contributors
team

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

236
agent commits
1,157
other considered commits
18
agent contributors
55.1%
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

214assisted
22autonomous

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
2026-0369.6%171
2026-0425.9%112
2026-058%301
2026-0614.7%245
2026-075.8%154
2026-085.6%303
2026-091.9%107

Peak month: 69.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic19614.1%
DevinCognition221.6%
Cursor AgentAnysphere151.1%
Other / generic agentVarious30.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • e1b41970 on GitHubRun ContributionMilestoneTests in the core CI shardClaude Code
  • 8c2d5480 on GitHubFormat milestone counts for English copy, not the user's localeClaude Code
  • f25ea23f on GitHubRecognize Slack huddle URLs in calendar eventsClaude Code
  • 92f5785e on GitHubPreserve observed calendar source IDsDevin
  • ae5745b6 on GitHubharden auto-export: async log writes, bounded collision loop, robust menu Devin
  • c7ccc280 on GitHubfeat: auto-export meeting notes as Markdown to a folderDevin
  • 3e523c6f on GitHubAssign PushToTalkEnablementPolicyTests to the dictation CI shard.Cursor Agent
  • 8794dbfa on GitHubFix dead Push to Talk after meetings-only onboarding.Cursor Agent
  • 248ec784 on GitHubSay transcribe instead of record on meeting join actionsCursor Agent
  • 274f5eb4 on GitHubFix issue #225: Pause media during dictation: already-paused media gets unOther / generic agent
  • 1f558f95 on GitHubFix issue #85: Meeting notes : Title should be meeting title not summary (Other / generic agent
  • e3031026 on GitHubFix issue #80: Meetings : Limit the list to the next 5 meetings (#83)Other / generic 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 window1,674
Merge commits removed−280
CI / dependency bots removed−1
Considered1,393

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin signatures →Swift AI coding statisticsCompare evidence across Swift 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 Muesli-HQ/muesli

Scan another repository

Try