Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Supabase CLI. Manage postgres migrations, run Supabase locally, deploy edge functions. Postgres backups. Generating types from your database schema.

01Result

supabase/cli ↗

supabase/cli AI coding statistics: 17.6%

of 877 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
17.6% agent · top contributor 59.1%14 contributors
team

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

154
agent commits
723
other considered commits
14
agent contributors
59.1%
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

146assisted
8autonomous

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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%62
2026-0319.1%47
2026-046.4%94
2026-0534.5%113
2026-0624.1%166
2026-0714.4%104
2026-0816.2%173
2026-0914.4%118

Peak month: 34.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic14016%
Cursor AgentAnysphere101.1%
GitHub CopilotGitHub60.7%

03Evidence

Inspect the matches

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

Matched commit samples

  • 99b093f0 on GitHubchore(repo): bump vitest, add smol top-level vitest config (#6567)Claude Code
  • db222409 on GitHubchore(repo): rewrite knip config to lean on plugin defaults (#6581)Claude Code
  • fd2629a9 on GitHubfix(ci): push the config release tag before the npm visibility probe (#662Claude Code
  • 3095e91c on GitHubfeat(cli): make the bundled pg-delta engine the only pg-delta implementatiCursor Agent
  • 2f672374 on GitHubtest(stack): derive image assertions from the service catalog (#6406)Cursor Agent
  • c3472e9b on GitHubfeat(cli): make shadow baseline cache opt-out (default ON) (#6403)Cursor Agent
  • 77080f0c on GitHubchore: sync API types from infrastructure (#5238)GitHub Copilot
  • 893c2840 on GitHubchore: sync API types from infrastructure (#5160)GitHub Copilot
  • 40bdcc65 on GitHubchore: add merge queue support to required GitHub Actions workflows (#5031GitHub 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 window1,283
Merge commits removed−43
CI / dependency bots removed−363
Considered877

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 →TypeScript AI coding statisticsCompare evidence across TypeScript repositories →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 supabase/cli

Scan another repository

Try