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

marimo-team/marimo ↗

marimo-team/marimo AI coding statistics: 10.3%

of 1,469 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
10.3% agent · top contributor 55.9%22 contributors
team

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

152
agent commits
1,317
other considered commits
22
agent contributors
55.9%
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

152assisted
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
2026-021.7%232
2026-034.4%252
2026-048.6%267
2026-054.4%160
2026-0623.8%151
2026-0722.7%203
2026-0818.4%114
2026-094.4%90

Peak month: 23.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere664.5%
GitHub CopilotGitHub453.1%
Claude CodeAnthropic402.7%
OpenAI CodexOpenAI30.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0419bb8f on GitHubfeat(table): `show only` columns from the column menu and explorer (#10768Cursor Agent
  • 1ee282bd on GitHubfix: map geoarrow to geoarrow-types (#10659)Cursor Agent
  • ad02456f on GitHubfix(tests): compare Pygments HTML output semantically across 2.19–2.21 (#1Cursor Agent
  • bb3532ac on GitHubfix: preserve unqualified references in methods (#10679)GitHub Copilot
  • 3a1b1dab on GitHubfeat: lint rule for private imports (#10580)GitHub Copilot
  • f1b3678a on GitHubfix: slurm script regression and docs/examples update (#10469)GitHub Copilot
  • 5aa823f9 on GitHubfix(markdown): render display math nested in list item continuations (#107Claude Code
  • b4181aba on GitHubfix(vega): use ctrl for chart pan/zoom on non-mac platforms (#3812) (#1049Claude Code
  • 3955fdf9 on GitHubfix(matplotlib): derive canvas draw scale from the backing store (#10626)Claude Code
  • b8c9ce29 on GitHubfeature: Infer file browser initial path from initial value (#10362)OpenAI Codex
  • 6faa194d on GitHubfeat: support default file browser selection (#10255)OpenAI Codex
  • 3b2f21a5 on GitHubbug: formatting of exposed classes preserves class decorators (#10042)OpenAI Codex

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 window1,530
Merge commits removed−0
CI / dependency bots removed−61
Considered1,469

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
marimo-team/marimo
Default branch
main
Resolved HEAD
fe5d9e65b39c34a80fff25d79278b50e9cc62472 ↗
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 position60th percentile

Midrank percentile; equal shares split the tied positions.

Repository
10.3%
Cohort median
6.3%
Share rank
98 / 247
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 marimo-team/marimo

Scan another repository

Try