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

getpaseo/paseo ↗

getpaseo/paseo AI coding statistics: 2.8%

of 4,127 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.8% agent · top contributor 27.2%42 contributors
org-wide

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

114
agent commits
4,013
other considered commits
42
agent contributors
27.2%
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

113assisted
1autonomous

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
2026-021.2%500
2026-033.1%557
2026-041.4%787
2026-051.1%716
2026-062.9%445
2026-075.7%435
2026-085.5%544
2026-092.8%143

Peak month: 5.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1112.7%
Cursor AgentAnysphere30.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0eac75be on GitHubfix(server): stop an expired application lease from permanently killing a Claude Code
  • 92442e74 on GitHubfix(server): reject pending Codex app-server requests on dispose (#4283)Claude Code
  • fa1f01eb on GitHubfeat(app): add fullscreen viewer for Mermaid diagrams on web (#4107)Claude Code
  • d0e1edca on GitHubfix(server): show the right thinking options for each Cursor model (#4180)Cursor Agent
  • 2347242c on GitHubfix(usage): read Cursor plan usage from cursor-agent auth.json (#3486)Cursor Agent
  • 3786cf35 on GitHubWait for Cursor ACP slash commands before listing. (#1099)Cursor 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 window4,581
Merge commits removed−216
CI / dependency bots removed−238
Considered4,127

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
getpaseo/paseo
Default branch
main
Resolved HEAD
64b1a62ed3ab86ced73393624087f050ecdd7d7f ↗
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 position38th percentile

Midrank percentile; equal shares split the tied positions.

Repository
2.8%
Cohort median
5.4%
Share rank
232 / 376
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 376.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 getpaseo/paseo

Scan another repository

Try