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.

NanoGPT (124M) in 90 seconds

01Result

KellerJordan/modded-nanogpt ↗

KellerJordan/modded-nanogpt AI coding statistics: 1.9%

of 837 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.9% agent · top contributor 37.5%6 contributors
team

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

16
agent commits
821
other considered commits
6
agent contributors
37.5%
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

16assisted
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
2026-020%27
2026-030%223
2026-042.6%190
2026-051.1%277
2026-068.1%99
2026-070%8
2026-080%13

Peak month: 8.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic151.8%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • a855e311 on GitHubTrack 3: Tail-EMA readout + RowFloor + Cautious Weight Decay -- 2690 stepsClaude Code
  • fb21a454 on GitHubTrack 3: Tail-EMA readout -- 3.28 in 2730 steps (n=8)Claude Code
  • 6f1c0035 on GitHubAdd track 3 result: MuonH with re-tuned aux AdamW reaches 3.28 in 3250 steClaude Code
  • e5136a3c on GitHubTrack 3 SOTA: PMuon (Preconditioned Muon) in 3225 stepsCursor Agent

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 window907
Merge commits removed−70
CI / dependency bots removed−0
Considered837

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 →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 KellerJordan/modded-nanogpt

Scan another repository

Try