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.

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

01Result

raullenchai/Rapid-MLX ↗

raullenchai/Rapid-MLX AI coding statistics: 48.6%

of 2,386 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
48.6% agent · top contributor 80.3%27 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

1,159
agent commits
1,227
other considered commits
27
agent contributors
80.3%
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

1159assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0261.5%78
2026-0395.8%119
2026-0478.2%101
2026-0558.8%204
2026-0671.6%416
2026-0757.3%293
2026-0829.5%899
2026-0924.3%276

Peak month: 95.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic115948.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 332c2628 on GitHubperf(template): keep Qwen3.5 tool-loop think blocks stable across turns (#Claude Code
  • c547059e on GitHubperf(mllm): resume Qwen3.5 hybrid prompts from recurrent-state checkpointsClaude Code
  • 38388ef4 on GitHubperf(desktop): ride the tool guidance on user rows, not the system row (#3Claude 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 window2,409
Merge commits removed−20
CI / dependency bots removed−3
Considered2,386

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 →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 raullenchai/Rapid-MLX

Scan another repository

Try