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.

Open source Granola AI Alternative

01Result

fastrepl/anarlog ↗

fastrepl/anarlog AI coding statistics: 14.3%

of 4,165 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.3% agent · top contributor 56.6%16 contributors
team

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

597
agent commits
3,568
other considered commits
16
agent contributors
56.6%
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

256assisted
341autonomous

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
2026-0243.6%822
2026-036%652
2026-045.7%419
2026-050%196
2026-060%404
2026-070%552
2026-0818.6%746
2026-099.9%374

Peak month: 43.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
DevinCognition3839.2%
Cursor AgentAnysphere1974.7%
Claude CodeAnthropic240.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • a97e8ac5 on GitHubRestore Teams speaker capture on Windows with endpoint loopback that folloDevin
  • 9eec2496 on GitHubLet invitees see and accept team invitations inside the app (#7548)Devin
  • faf02348 on GitHubfix(speaker): scope Apply-to-all assignments and preserve them safely throDevin
  • 711bc015 on GitHubWrite a best multilingual AI notetaker comparison (#7171)Cursor Agent
  • cbb7d60e on GitHubWrite a first-party Fathom review (#7172)Cursor Agent
  • 9785ac0e on GitHubWrite an Is Granola AI safe post on consent and the class action (#7170)Cursor Agent
  • 94cc5912 on GitHubForward dictionary hints and speaker diarization through OpenRouter transcClaude Code
  • 7e838236 on GitHubfeat(db-app): sync transcript words as chunks (#7523)Claude Code
  • ec1d4a1d on GitHubfeat(db-app): sync tags, session tags, folders, and daily notes (#7522)Claude Code

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 window4,180
Merge commits removed−11
CI / dependency bots removed−4
Considered4,165

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 →Rust AI coding statisticsCompare evidence across Rust 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 fastrepl/anarlog

Scan another repository

Try