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.

Python Client for Supabase. Query Postgres from Flask, Django, FastAPI. Python user authentication, security policies, edge functions, file storage, and realtime data streaming. Good first issue.

01Result

supabase/supabase-py ↗

supabase/supabase-py AI coding statistics: 15.2%

of 46 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
Too little recent activity to publish. Only 46 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.
15.2% agent · top contributor 71.4%3 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

7
agent commits
39
other considered commits
3
agent contributors
71.4%
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

7assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0214.3%7
2026-030%6
2026-0444.4%9
2026-050%4
2026-0650%2
2026-070%7
2026-0814.3%7
2026-090%4

Peak month: 50%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic613%
Cursor AgentAnysphere12.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • cb3857cf on GitHubfeat: update X-Client-Info to use structured semicolon-delimited metadata Claude Code
  • 908b8b4e on GitHubchore: add missing @ prefix to o-santi in CODEOWNERS (#1478)Claude Code
  • 01d84e0d on GitHubrefactor: rename anon key → publishable key, service role key → secret keyClaude Code
  • 0490201f on GitHubfix(postgrest): align rpc maybe_single with select (#1555)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 window74
Merge commits removed−0
CI / dependency bots removed−28
Considered46

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python 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/supabase-py

Scan another repository

Try