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.

Running a big model on a small laptop

01Result

danveloper/flash-moe ↗

danveloper/flash-moe AI coding statistics: 95.8%

of 144 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

95.8% agent · top contributor 100%1 contributor

individual

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

138

agent commits

other considered commits

agent contributors

100%

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

138assisted

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.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	138	95.8%

03Evidence

Inspect the matches

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

Matched commit samples

3601d418 on GitHubQ4 optimization: FMA kernel +12%, 58 experiments documentedClaude Code
d9e91d4e on GitHubfeat: tool calling (bash) + custom system prompt (~/.flash-moe/system.md)Claude Code
15b8eb51 on GitHubupdate progress.png — 397B only, no 122B/35B runsClaude 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 window	144
Merge commits removed	−0
CI / dependency bots removed	−0
Considered	144

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 →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 danveloper/flash-moe

Scan another repository

Try