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

vercel/ai ↗

vercel/ai AI coding statistics: 12.8%

of 1,693 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12.8% agent · top contributor 57.1%36 contributors
team

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

217
agent commits
1,476
other considered commits
36
agent contributors
57.1%
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

213assisted
4autonomous

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%1
2026-0212.1%182
2026-039.8%183
2026-048.6%222
2026-0520.6%243
2026-0619.8%237
2026-0717.1%252
2026-087.1%254
2026-090%119

Peak month: 20.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic17110.1%
Cursor AgentAnysphere482.8%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 5366b7ba on GitHubfix(minimax): support 480P and 768P video resolutions (#20004)Claude Code
  • 86892f3f on GitHubfix(openai-compatible): preserve unmapped usage fields in usage.raw (#1856Claude Code
  • 39bd17eb on GitHubfix(harness-pi): deliver tool results submitted after cross-process resumeClaude Code
  • 7439d7ab on GitHubfix(openai): restore responses workflow deserialization (#15589)Cursor Agent
  • 79e133cc on GitHubfeat(video): externalize polling control and webhook support for generateVCursor Agent
  • 86a84c90 on GitHubfix(harness): emit an abort part instead of an AbortError error part when Cursor Agent
  • ed313f7e on GitHubci(release): delete pre.json before snapshot versioning to support beta reGitHub Copilot

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 window2,634
Merge commits removed−0
CI / dependency bots removed−941
Considered1,693

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
vercel/ai
Default branch
main
Resolved HEAD
662d7e579f34635ad5275fd2538a85a5c0c643eb ↗
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 position68th percentile

Midrank percentile; equal shares split the tied positions.

Repository
12.8%
Cohort median
5.4%
Share rank
121 / 376
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 376.

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 →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 vercel/ai

Scan another repository

Try