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.

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight! Android, Linux waitlist open! A local Wispr Flow alternative. Follow https://x.com/fluidvoiceapp for more

01Result

altic-dev/FluidVoice ↗

altic-dev/FluidVoice AI coding statistics: 6.1%

of 739 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

6.1% agent · top contributor 33.3%13 contributors

org-wide

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

agent commits

694

other considered commits

agent contributors

33.3%

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

45assisted

0autonomous

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

Peak month: 15.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	39	5.3%
Cursor Agent	Anysphere	5	0.7%
OpenAI Codex	OpenAI	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

1b114073 on GitHubHonor "Send Custom Prompt Only" for dictation-shortcut prompt overridesClaude Code
c1f8c22a on GitHubfix(transcription): accept .opus/.oga files in file transcriptionClaude Code
1bb3ff32 on GitHubfix(dictionary): allow whitespace-only replacements (e.g. a pasted newlineClaude Code
ac3f78e5 on GitHubswiftformat with Swift 5 (changed files only)Cursor Agent
2ee6ffb2 on GitHubAdd persistent history for file transcriptionsCursor Agent
632e45e7 on GitHubswiftformat with Swift 5 (MeetingTranscriptionView only)Cursor Agent
9ff3a440 on GitHubtranscribing - text fix for bottom overlay - mid fixOpenAI Codex

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 window	893
Merge commits removed	−154
CI / dependency bots removed	−0
Considered	739

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 altic-dev/FluidVoice

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	8.6%	81
2026-03	15.9%	88
2026-04	4.2%	71
2026-05	0%	39
2026-06	5.6%	143
2026-07	2.4%	123
2026-08	8.3%	121
2026-09	0%	73