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.

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

01Result

Blaizzy/mlx-audio ↗

Blaizzy/mlx-audio AI coding statistics: 17.1%

of 555 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

17.1% agent · top contributor 24.2%21 contributors

org-wide

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

agent commits

460

other considered commits

agent contributors

24.2%

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

95assisted

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: 36.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	91	16.4%
OpenAI Codex	OpenAI	4	0.7%

03Evidence

Inspect the matches

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

Matched commit samples

8cb1e301 on GitHubstyle: apply isort to LFM2.5-Audio testsClaude Code
0114eb9a on GitHubdocs: skip audio EOS frames in LFM2.5-Audio interleaved examplesClaude Code
2d1529db on GitHubVoxtral: stop on <pad> (11), not on the text token 32000Claude Code
752b3d64 on GitHubAlign Breeze generation sampling and streamingOpenAI Codex
903903f8 on GitHubAdd Breeze architecture and checkpoint loaderOpenAI Codex
1a079928 on GitHubAdd Breeze CLI aliases and documentationOpenAI 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	758
Merge commits removed	−203
CI / dependency bots removed	−0
Considered	555

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Python AI coding statisticsCompare evidence across Python 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 Blaizzy/mlx-audio

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	14.7%	34
2026-03	11.4%	140
2026-04	20.5%	78
2026-05	9.3%	75
2026-06	8.2%	49
2026-07	19.2%	52
2026-08	36.6%	93
2026-09	8.8%	34