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.

The personal finance app for everyone (by everyone)

01Result

we-promise/sure ↗

we-promise/sure AI coding statistics: 22.4%

of 1,251 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
22.4% agent · top contributor 17.1%72 contributors
org-wide

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

280
agent commits
971
other considered commits
72
agent contributors
17.1%
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

279assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0222.4%125
2026-0342.6%122
2026-0417.8%118
2026-057.6%224
2026-066.2%225
2026-0731.5%108
2026-0839.4%193
2026-0927.9%136

Peak month: 42.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic24519.6%
Cursor AgentAnysphere211.7%
GitHub CopilotGitHub141.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 5a198fb9 on GitHubfix(snaptrade): trust reported trade amount and import trade fees (#3507)Claude Code
  • 871f4785 on GitHubSkip investment accounts when detecting bills and income (#3565)Claude Code
  • 44bbfb2f on GitHubfeat(accounts): add expand/collapse all and default-expanded groups to sidClaude Code
  • 8cffeaae on GitHubfix(ds): resolve remaining DS Drift findings (#1971) (#2978)Cursor Agent
  • fa5c5444 on GitHubMake report income/expense categories clickable (#2923)Cursor Agent
  • b7540658 on GitHubfix(i18n): drop redundant Questrade t() default: strings (#2976)Cursor Agent
  • 475dbbfb on GitHubfix: Enable and persist notes and tags on split child transactions (#1535)GitHub Copilot
  • 6f195c6c on GitHubHide nested budget categories in the Budget spent donut (#1544)GitHub Copilot
  • 3199c9b7 on GitHubPrevent long category labels from overflowing or crowding adjacent controlGitHub 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 window1,407
Merge commits removed−41
CI / dependency bots removed−115
Considered1,251

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 →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 we-promise/sure

Scan another repository

Try