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

vitessio/vitess ↗

vitessio/vitess AI coding statistics: 36.9%

of 490 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
36.9% agent · top contributor 53.6%28 contributors
team

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

181
agent commits
309
other considered commits
28
agent contributors
53.6%
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

169assisted
12autonomous

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
2026-028%87
2026-0356.7%67
2026-0428.4%67
2026-0527.8%54
2026-0652.5%61
2026-0744.3%79
2026-0847.6%42
2026-0945.5%33

Peak month: 56.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic15932.4%
GitHub CopilotGitHub275.5%
DevinCognition10.2%
Cursor AgentAnysphere10.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • fc22202c on GitHubci: bump Apache ZooKeeper to 3.9.6 and bound download retries (#21099)Claude Code
  • 76f3e844 on GitHubcache: remove write-only timestamp from LRUCache entries (#21080)Claude Code
  • a7a96c44 on GitHubfeat(s3): use transfer manager for parallel S3 downloads during restore (#Claude Code
  • 35daf77f on GitHubvtorc: replace --cells-to-watch with --cells-no-recovery (#20022)GitHub Copilot
  • eccf6ee0 on GitHubPreserve Materialize target data on cancel (#20823)GitHub Copilot
  • 15366bf4 on GitHubmysqlctl: prevent closeBackupFiles from cancelling context on successful fGitHub Copilot
  • 7c9e1486 on GitHubVReplication: LookupVindex streams must not follow TABLES journals (#20917Devin
  • 4425351c on GitHubApplySchema: add session variable options (#20654)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 window639
Merge commits removed−0
CI / dependency bots removed−149
Considered490

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
vitessio/vitess
Default branch
main
Resolved HEAD
1cf37324b47163986fa90f13df602b5756292381 ↗
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.

CohortGo · 132 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 62 of 194 ecosystem repositories excluded
Agent-commit share position91st percentile

Midrank percentile; equal shares split the tied positions.

Repository
36.9%
Cohort median
2.8%
Share rank
13 / 132
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 132.

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 →Devin commitsBrowse repositories with detected Devin 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 vitessio/vitess

Scan another repository

Try