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.

Business intelligence as code: build fast, interactive data visualizations in SQL and markdown

01Result

evidence-dev/evidence ↗

evidence-dev/evidence AI coding statistics: 40.4%

of 47 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
Too little recent activity to publish. Only 47 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.
40.4% agent · top contributor 78.9%3 contributors
individual

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

19
agent commits
28
other considered commits
3
agent contributors
78.9%
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

19assisted
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
2026-020%11
2026-0855.6%27
2026-0944.4%9

Peak month: 55.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere1123.4%
Claude CodeAnthropic817%

03Evidence

Inspect the matches

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

Matched commit samples

  • f4ef042c on GitHubfix(table): only merge dimension cells within the same parent group (#2043Cursor Agent
  • 27a4cbb9 on GitHubfix(pdf): parent checkboxes toggle whole subtree in contents picker (#2039Cursor Agent
  • f672b3f0 on GitHubfix(translations): add .sql accessor for use inside SQL string literals (#Cursor Agent
  • cbbd22cc on GitHubfix(charts): stop duplicate empty-attribute validation errors on series chClaude Code
  • 0c35a3c8 on GitHubfix(table_filter): shrink value list to content instead of fixed 300px (#1Claude Code
  • 3863ddb2 on GitHubfix(table): quote hidden dimension link/image/logo + row-color aliases forClaude Code

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 window53
Merge commits removed−5
CI / dependency bots removed−1
Considered47

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 →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 evidence-dev/evidence

Scan another repository

Try