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.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

MakazhanAlpamys/Soup ↗

MakazhanAlpamys/Soup AI coding statistics: 33.5%

of 1,303 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
33.5% agent · top contributor 51%31 contributors
team

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

437
agent commits
866
other considered commits
31
agent contributors
51%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

437assisted
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
2026-02100%9
2026-0362.1%116
2026-0435.2%105
2026-0583.2%113
2026-060%70
2026-076.2%177
2026-088%415
2026-0960.7%298

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic43733.5%

Inspect the matches

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

Matched commit samples

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 window1,304
Merge commits removed−1
CI / dependency bots removed−0
Considered1,303

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 MakazhanAlpamys/Soup

Scan another repository