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

monkeytypegame/monkeytype ↗

monkeytypegame/monkeytype AI coding statistics: 3.2%

of 710 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.2% agent · top contributor 39.1%11 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

23
agent commits
687
other considered commits
11
agent contributors
39.1%
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

23assisted
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
2026-021.1%92
2026-037.5%173
2026-043.4%59
2026-051.1%93
2026-061.1%185
2026-073.8%80
2026-083.6%28

Peak month: 7.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub192.7%
Claude CodeAnthropic60.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 06f52c89 on GitHubfeat(result): option to copy slow words list with filtering (@vrutant08) (GitHub Copilot
  • e113dff1 on GitHubrefactor: convert the rest of test state to solid (@miodec) (#8261)GitHub Copilot
  • 476fe5e0 on GitHubrefactor: solid live stats (@miodec) (#8248)GitHub Copilot
  • fa5acc53 on GitHubrefactor(generator): include commit spaces in generated words (@miodec, @LClaude Code
  • 9ab31b9f on GitHubfix(quick-restart): quick restart warning firing for wrong events in long Claude Code
  • b40fb259 on GitHubchore: add Claude Code GitHub Workflow (@miodec) (#7617)Claude 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 window759
Merge commits removed−0
CI / dependency bots removed−49
Considered710

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
monkeytypegame/monkeytype
Default branch
master
Resolved HEAD
91bd24bb8513785c7364cbea29296ff7adafac41 ↗
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.

CohortJS/TS · 376 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 194 of 570 ecosystem repositories excluded
Agent-commit share position41st percentile

Midrank percentile; equal shares split the tied positions.

Repository
3.2%
Cohort median
5.4%
Share rank
219 / 376
0th50th100th

Percentile = (repositories below + half of 9 tied repositories) ÷ 376.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot 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 monkeytypegame/monkeytype

Scan another repository

Try