Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

karpathy/nanochat ↗

karpathy/nanochat AI coding statistics: 5.6%

of 124 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.6% 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.

7
agent commits
117
other considered commits
1
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

7assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-010%3
2026-020%60
2026-035.7%35
2026-040%6
2026-050%1
2026-0726.3%19

Peak month: 26.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic75.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 3616a029 on GitHubadd a comment clarifying that RoPE here rotates by -theta (transpose of thClaude Code
  • 2ce972a3 on GitHubfix token_bytes calculation to use raw token bytes instead of round-trippiClaude Code
  • 5e43f1eb on GitHubdocs: note that MPS handles bf16 fine on recent macOS (opt in via NANOCHATClaude 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 window151
Merge commits removed−27
CI / dependency bots removed−0
Considered124

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

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
karpathy/nanochat
Default branch
master
Resolved HEAD
92d63d4e8bb4df75c3b71618f31ddde2378b2bcd ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position46th percentile

Midrank percentile; equal shares split the tied positions.

Repository
5.6%
Cohort median
6.3%
Share rank
132 / 247
0th50th100th

Percentile = (repositories below + half of 5 tied repositories) ÷ 247.

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 karpathy/nanochat

Scan another repository

Try